© 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. 11970
    Prev
    Next
    INDEX
    Explanations

    file path manipulation, joining, and resolving

    oai_token-act-pair · gemini-2.0-flash

    file paths and code

    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
    quellen
    -0.49
    mezzo
    -0.47
    quién
    -0.47
    艇
    -0.45
     Katz
    -0.43
    CURSOR
    -0.43
    relli
    -0.42
    getContentPane
    -0.42
    Orléans
    -0.41
    quelle
    -0.41
    POSITIVE LOGITS
    expandindo
    0.87
     Roskov
    0.73
     antara
    0.73
     BETWEEN
    0.66
     />';
    0.65
    IntoConstraints
    0.62
     initComponents
    0.62
    ArgsConstructor
    0.62
    Autoritní
    0.62
     between
    0.61
    Activations Density 0.537%

    No Known Activations