© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13283
    Prev
    Next
    INDEX
    Explanations

    locations in a document where an equation or formula is being introduced or derived.

    oai_token-act-pair · gemini-2.0-flash

    location/association words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ậc
    -0.48
    ogueira
    -0.46
    外人
    -0.46
     conf
    -0.45
    ignen
    -0.43
     Coliseum
    -0.43
    ENSOR
    -0.42
    piram
    -0.42
    Confirmation
    -0.42
     cref
    -0.41
    POSITIVE LOGITS
    MLLoader
    0.91
    Xna
    0.75
     lenker
    0.73
    UserScript
    0.73
     autorytatywna
    0.70
    AttributeSet
    0.69
     ligiloj
    0.67
    Tembelea
    0.63
     ſhould
    0.62
     muſt
    0.62
    Activations Density 12.091%

    No Known Activations