⚠️ Rolling Release
Neuronpedia is finalizing data uploads and feature label generation, a process which we expect to be completed by February 14, 2026.
The artifacts in Gemma Scope 2 HuggingFace are complete and available for use.
Gemma Scope 2
DemoExamining Safety-Relevant Features and Circuits in Gemma 3
👋 New Here?
If you're new to interpretability (the science of understanding what happens inside AI), we recommend you start with the original "Exploring Gemma Scope", which has more beginner-friendly interactive demos and content.
This Gemma Scope 2 demo focuses on exploring safety-relevant features in Gemma 3 27B-IT, the largest model in the new Gemma 3 model series. Since the Gemma Scope 2 release also includes transcoders, cross-layer transcoders, and crosscoders, Neuronpedia is also adding support for circuit tracing with those new artifacts.
🔢 Sections
🛡️
Safety & Alignment
Explore safety and alignment relevant features in Gemma 3.
🔌
Circuit Tracing
Using prompts to activate and trace Gemma 3's internal reasoning steps.
📖
Dashboards + Inference
See top activating examples, search, and test with inference.