© 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. 15635
    Prev
    Next
    INDEX
    Explanations

    technical language in scientific papers (especially chemistry and medicine) and insurance policies, and code.

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical 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
    orsal
    -0.55
    nonatomic
    -0.54
     الحره
    -0.53
    جوايز
    -0.53
    Phaser
    -0.49
    roek
    -0.48
     zape
    -0.48
     betweenstory
    -0.47
    modium
    -0.47
    rician
    -0.47
    POSITIVE LOGITS
    MigrationBuilder
    0.57
    LookAnd
    0.54
    SourceChecksum
    0.52
    writeFieldEnd
    0.52
     adipis
    0.50
    prnewswire
    0.50
     TType
    0.49
    bootstrapcdn
    0.47
     оригіналу
    0.47
     CascadeType
    0.46
    Activations Density 0.511%

    No Known Activations