© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9788
    Prev
    Next
    INDEX
    Explanations

    the word "cook" and related words such as "cooking" and "cooked"

    oai_token-act-pair · gemini-2.0-flash

    cooking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    opardy
    -0.76
    joi
    -0.60
    IsContent
    -0.58
    ষ্
    -0.56
    Boiling
    -0.55
    mi
    -0.55
     facie
    -0.55
    gridx
    -0.54
    Ifc
    -0.54
    ский
    -0.52
    POSITIVE LOGITS
     Jefus
    0.78
    tonode
    0.75
     Réponses
    0.74
     Chriftian
    0.73
     Reſ
    0.71
     itſelf
    0.70
    QMetaType
    0.70
    oczes
    0.70
     autorytatywna
    0.68
     Diſ
    0.68
    Activations Density 0.708%

    No Known Activations