© 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. 1885
    Prev
    Next
    INDEX
    Explanations

    technical terms, especially in scientific and medical contexts, but also including some sports and mundane words.

    oai_token-act-pair · 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
    GenerationType
    -0.71
    :][
    -0.69
     GenerationType
    -0.67
    awtextra
    -0.63
     berries
    -0.63
    CloseOperation
    -0.62
    emd
    -0.61
    mord
    -0.59
    InSection
    -0.56
    ']").
    -0.55
    POSITIVE LOGITS
    ⓧ
    0.79
     reafon
    0.75
     Tapia
    0.75
     Efq
    0.73
    didSet
    0.72
     Pickering
    0.72
     Nikita
    0.70
     Moonlight
    0.69
     themſelves
    0.69
     reaſon
    0.69
    Activations Density 9.001%

    No Known Activations