© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Gemma Scope 2
    5. Gemma-3-27B-IT
    7. Transcoder - 262k
    9. 40-GEMMASCOPE-2-TRANSCODER-262K
    gemma-3-27b-it · 40-gemmascope-2-transcoder-262k
    Source from gemma-scope-2 · Transcoder - 262k · Layer 40
    Jump to Source/SAE
    Jump to Feature
    INDEX

    Configuration

    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    No Configuration Found

    Search Explanations

    Browse

    Features in GEMMA-3-27B-IT@40-gemmascope-2-transcoder-262k
    1. Hover over a feature on the left to preview its details.
    2. Click a feature to lock it and interact with it.