© 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. 634
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and symbols

    oai_token-act-pair · gemini-2.0-flash

    inequalities

    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
    Negative Logits
    ürger
    -0.57
     niyang
    -0.53
     zó
    -0.52
    JsonInclude
    -0.50
     насеље
    -0.49
     areal
    -0.47
    Ży
    -0.46
     VJ
    -0.45
     inov
    -0.45
    oubliez
    -0.44
    POSITIVE LOGITS
    Diwedd
    0.63
     religieuses
    0.62
     affitto
    0.61
    帖最后由
    0.61
    SequentialGroup
    0.59
    Билгалдахарш
    0.59
     للاسماء
    0.57
     gynhyrchwyd
    0.57
     nahilalakip
    0.57
     Best
    0.57
    Activations Density 3.881%

    No Known Activations