© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4726
    Prev
    Next
    INDEX
    Explanations

    numbers related to sports scores and statistics

    oai_token-act-pair · gemini-2.0-flash

    reviews with scores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    verty
    -0.53
    yntaxException
    -0.53
    Дорогие
    -0.45
    ules
    -0.44
    になれば
    -0.43
    лочки
    -0.43
    jooq
    -0.43
    $
    -0.43
     
    -0.43
    esez
    -0.42
    POSITIVE LOGITS
     itſelf
    0.76
     grades
    0.65
     Performances
    0.60
    perform
    0.60
     myſelf
    0.59
     Theſe
    0.59
     Perform
    0.59
     performances
    0.58
     fared
    0.57
    دانشنامهٔ
    0.57
    Activations Density 1.132%

    No Known Activations