© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16015
    Prev
    Next
    INDEX
    Explanations

    scientific findings particularly related to insulin signaling and diabetes

    oai_token-act-pair · gemini-2.0-flash

    insulin resistance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    MigrationBuilder
    -0.82
    IntoConstraints
    -0.77
     EconPapers
    -0.73
     AssemblyCulture
    -0.69
    contentLoaded
    -0.63
    featureID
    -0.62
     للمعارف
    -0.61
     jLabel
    -0.61
     Meksiku
    -0.60
    qrstuvwxyz
    -0.60
    POSITIVE LOGITS
     consultato
    0.49
    тарь
    0.48
    Obrázky
    0.47
    iade
    0.46
    iscus
    0.46
     surla
    0.44
    cides
    0.44
    oppo
    0.43
    くださいね
    0.42
    aldehyde
    0.42
    Activations Density 8.872%

    No Known Activations