© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11951
    Prev
    Next
    INDEX
    Explanations

    code snippets, specifically PHP and UI related code

    oai_token-act-pair · gemini-2.0-flash

    pessoa

    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
    ConstraintMaker
    -0.63
    oredCriteria
    -0.60
    SourceChecksum
    -0.57
    ArgsConstructor
    -0.56
     Signalez
    -0.54
    NameInMap
    -0.53
     protoimpl
    -0.51
     eventdata
    -0.50
     initComponents
    -0.50
    Hare
    -0.50
    POSITIVE LOGITS
     ویکی‌پدیای
    0.79
     tromper
    0.63
     étrangères
    0.61
     brancas
    0.58
     couper
    0.57
     culturelles
    0.56
    таратура
    0.56
    karna
    0.55
    مصادر
    0.54
     térm
    0.54
    Activations Density 0.437%

    No Known Activations