© 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. 6321
    Prev
    Next
    INDEX
    Explanations

    a variety of seemingly unrelated tokens including phone numbers, statistics, patent numbers, and the word "transform"

    oai_token-act-pair · gemini-2.0-flash

    code/scientific texts

    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
    PerformLayout
    -0.73
    sidemargin
    -0.64
     WaitForSeconds
    -0.63
    DotNetBar
    -0.62
     estekak
    -0.61
     defaultstate
    -0.61
    Viited
    -0.60
    opsida
    -0.59
    \"]
    -0.58
     ویکی‌پدیای
    -0.56
    POSITIVE LOGITS
    migrationBuilder
    0.60
     AssemblyCulture
    0.54
    Hintergrund
    0.49
    पया
    0.49
     Worcester
    0.48
    zler
    0.47
    fre
    0.47
     bilinear
    0.47
    ècie
    0.47
    RenderAtEndOf
    0.46
    Activations Density 2.356%

    No Known Activations