Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma Scope 2: Comprehensive Suite of SAEs and Transcoders for Gemma 3
    Gemma Scope 2: Comprehensive Suite of SAEs and Transcoders for Gemma 3
    Language Model Interpretability Team, Google DeepMind
    ·huggingface.co ↗·colab.research.google.com ↗
    gemma-scope-2
    ⚠️ Rolling Release
    An initial release of artifacts and datasets are available now, with more being actively released on a rolling basis.
    All artifacts are expected to be finalized by December 31, 2025.
    Some data may be replaced or updated during this final verification and fine-tuning process. Please check the HuggingFace for details.

    Jump To

    Jump to Source/SAE
    Jump to Feature
    INDEX
    Random Feature

    Search Explanations

    Search via Inference

    Run Example Search

    Browse

    Features in GEMMA-3-4B@9-gemmascope-2-res-16k
    1. Hover over a feature on the left to preview its details.
    2. Click a feature to lock it and interact with it.