© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8060
    Prev
    Next
    INDEX
    Explanations

    words and code used in back-end programming

    oai_token-act-pair · gemini-2.0-flash

    code database

    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
    Negative Logits
    prüche
    -0.51
    IntoConstraints
    -0.48
     ProtoMessage
    -0.48
    PreAuthorize
    -0.47
     habido
    -0.46
    homonymie
    -0.43
    Aiheesta
    -0.42
    contentLoaded
    -0.42
     flesta
    -0.42
    :✨
    -0.42
    POSITIVE LOGITS
    VersionUID
    0.71
    databind
    0.65
     ब्रेकडाउन
    0.58
    matchCondition
    0.57
    GraphicsUnit
    0.56
     Venise
    0.56
    gms
    0.54
     Intent
    0.54
     digital
    0.54
    CreateMap
    0.54
    Activations Density 1.885%

    No Known Activations