© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8243
    Prev
    Next
    INDEX
    Explanations

    words or characters that are used in medical texts, banking, or in mathematical proofs.

    oai_token-act-pair · gemini-2.0-flash

    Technical/Scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     carottes
    -0.47
    anna
    -0.44
    indelijk
    -0.43
     thereunder
    -0.43
     zug
    -0.42
     unknownFields
    -0.42
     rather
    -0.42
    dziew
    -0.41
    lainen
    -0.41
     pilote
    -0.40
    POSITIVE LOGITS
    SourceChecksum
    0.66
     externi
    0.61
     doubtnut
    0.60
     nahilalakip
    0.60
    PerformLayout
    0.59
    aarrggbb
    0.59
     Waray
    0.57
     contem
    0.57
     ModelExpression
    0.56
     Voy
    0.56
    Activations Density 4.566%

    No Known Activations