© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15292
    Prev
    Next
    INDEX
    Explanations

    phrases with mathematical or scientific words

    oai_token-act-pair · gemini-2.0-flash

    technical programming terms

    np_token-act-pair-logits · gpt-4o-mini

    math/computer code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     asymmetric
    -0.52
    carboxylic
    -0.51
     wreath
    -0.50
     Versorgung
    -0.48
    wieś
    -0.48
     <>",
    -0.47
     nth
    -0.46
     vâ
    -0.46
    Gambas
    -0.46
     Hanley
    -0.44
    POSITIVE LOGITS
    contentLoaded
    0.66
     mergeFrom
    0.63
    Vidite
    0.63
    isContained
    0.58
    <!--[
    0.56
     violenza
    0.56
     määrä
    0.56
    antMatchers
    0.56
    randomUUID
    0.55
     sẻ
    0.54
    Activations Density 0.758%

    No Known Activations