© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14189
    Prev
    Next
    INDEX
    Explanations

    text related to times of the day, dress codes and business hours

    oai_token-act-pair · gemini-2.0-flash

    hours, open

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    RenderAtEndOf
    -0.72
     Paglinawan
    -0.67
     OnClickListener
    -0.60
    UnsafeEnabled
    -0.60
     StatelessWidget
    -0.59
    migrationBuilder
    -0.56
    ADORES
    -0.56
    addCriterion
    -0.56
    niająca
    -0.56
    PLICATIONS
    -0.55
    POSITIVE LOGITS
     spéciaux
    0.55
     piena
    0.48
    انيف
    0.47
    ftagPool
    0.46
     estekak
    0.46
     acolo
    0.45
     voyez
    0.44
     peł
    0.44
     Biôgrafia
    0.43
     później
    0.43
    Activations Density 1.552%

    No Known Activations