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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6831
    Prev
    Next
    INDEX
    Explanations

    instances where inhibiting something is mentioned

    oai_token-act-pair · gemini-2.0-flash

    would

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſte
    -0.63
    AxisAlignment
    -0.60
     بتاريخ
    -0.57
     charité
    -0.57
     sauvages
    -0.56
     élev
    -0.56
     nonUne
    -0.56
     raiſ
    -0.55
     reaſon
    -0.55
     évêque
    -0.55
    POSITIVE LOGITS
     would
    3.13
    would
    2.72
     Would
    2.56
    Would
    2.52
     WOULD
    2.31
     wouldn
    1.73
     sería
    1.58
     wou
    1.53
     zouden
    1.52
    wouldn
    1.52
    Activations Density 3.151%

    No Known Activations