© 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. 10475
    Prev
    Next
    INDEX
    Explanations

    words in languages other than English, particularly those related to computing, politics, or social interaction

    oai_token-act-pair · gemini-2.0-flash

    multiple languages

    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
    DoubleQuotes
    -0.61
    يميديا
    -0.54
    <bos>
    -0.53
    migrationBuilder
    -0.50
    MigrationBuilder
    -0.50
    tamanya
    -0.46
     StatelessWidget
    -0.46
    StoreMessageInfo
    -0.45
     disponibilités
    -0.44
    swt
    -0.42
    POSITIVE LOGITS
    IsContent
    0.71
     initComponents
    0.66
    principalColumn
    0.60
     murale
    0.60
    @[+][
    0.59
    troppo
    0.58
    setVerticalGroup
    0.57
     Paglinawan
    0.56
     tentative
    0.56
     recrystal
    0.55
    Activations Density 1.661%

    No Known Activations