© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 734
    Prev
    Next
    INDEX
    Explanations

    arrow functions and the word "function" in code.

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    IKAN
    -0.64
    VIAF
    -0.58
    uthorized
    -0.56
    fible
    -0.55
    simus
    -0.53
     kew
    -0.53
     Audiodateien
    -0.52
    saldo
    -0.52
    mappedBy
    -0.52
    GetEnumerator
    -0.52
    POSITIVE LOGITS
    <bos>
    1.60
     Administrativna
    0.69
    WindowConstants
    0.66
    évaluateur
    0.60
     ostavi
    0.57
     '\\;'
    0.55
     समीक्षाओं
    0.54
    adpleegd
    0.54
    apimachinery
    0.53
    ---*/
    0.52
    Activations Density 1.781%

    No Known Activations