© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13304
    Prev
    Next
    INDEX
    Explanations

    phrases containing words that are related to improving situations and understanding things

    oai_token-act-pair · gemini-2.0-flash

    societal issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    migrationBuilder
    -0.77
    PhysRevD
    -0.68
    
    -0.63
     kasarigan
    -0.59
    awtextra
    -0.59
    Erreferentziak
    -0.56
    IVEREF
    -0.56
    providedIn
    -0.56
    TagMode
    -0.55
     مشين
    -0.54
    POSITIVE LOGITS
    StoreMessageInfo
    0.64
     ब्रेकडाउन
    0.62
     GIPHY
    0.62
     Anſ
    0.61
     cowardice
    0.59
     Reſ
    0.59
     Hift
    0.57
     parentage
    0.56
     pareil
    0.55
     dilatation
    0.55
    Activations Density 9.279%

    No Known Activations