© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7496
    Prev
    Next
    INDEX
    Explanations

    variables, operators, and notation commonly used in math and statistics, especially those that are enclosed in '$' symbols and used in formulas

    oai_token-act-pair · gemini-2.0-flash

    Mathematical notation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     betweenstory
    -0.58
     forty
    -0.43
    myn
    -0.42
    TagHelper
    -0.41
    рация
    -0.41
    __':
    -0.41
    ÄT
    -0.40
     nine
    -0.39
     seven
    -0.39
     eight
    -0.39
    POSITIVE LOGITS
    Дереккөздер
    0.69
    таратура
    0.67
    Jereo
    0.63
    1
    0.59
     AspNetCore
    0.58
     оригіналу
    0.57
    XmlAccessType
    0.57
     MaterialApp
    0.56
     financieras
    0.55
    oneta
    0.54
    Activations Density 1.761%

    No Known Activations