© 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. 3794
    Prev
    Next
    INDEX
    Explanations

    text describing film production plans

    oai_token-act-pair · gemini-2.0-flash

    book to film adaptation

    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
     Normdatei
    -0.79
    :✨
    -0.78
     lenker
    -0.76
     تانيه
    -0.68
    ThroughAttribute
    -0.65
    BeginInit
    -0.65
     مشين
    -0.63
     ModelExpression
    -0.60
     transférez
    -0.60
    GEBURTSDATUM
    -0.60
    POSITIVE LOGITS
    énario
    0.50
     poaching
    0.44
    KommentareTeilen
    0.43
    verwijspagina
    0.42
     share
    0.42
    Dund
    0.42
    brd
    0.41
    Plans
    0.40
     expanding
    0.40
    openqa
    0.40
    Activations Density 0.350%

    No Known Activations