© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6177
    Prev
    Next
    INDEX
    Explanations

    Chinese characters and PHP code related to dictionaries and text analysis

    oai_token-act-pair · gemini-2.0-flash

    编译

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    hdys
    -0.69
     Wartawan
    -0.65
    "]));
    -0.63
    <?
    -0.60
    TryParse
    -0.60
    $")
    -0.59
     concernés
    -0.57
    mereka
    -0.57
    tersebut
    -0.57
    "]];
    -0.56
    POSITIVE LOGITS
     Bourgoin
    0.71
    TintMode
    0.53
    postsleuth
    0.48
    NamedQueries
    0.47
    cre
    0.46
     ryt
    0.45
    ArrowToggle
    0.43
    便
    0.42
    ritz
    0.42
     MPL
    0.42
    Activations Density 1.308%

    No Known Activations