© 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. 8097
    Prev
    Next
    INDEX
    Explanations

    tokens related to programming scripts and required arguments or configurations or cortical.

    oai_token-act-pair · 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
    <bos>
    -0.56
     Aal
    -0.44
     سا
    -0.40
     dedic
    -0.40
     elit
    -0.40
     кандида
    -0.40
     menggel
    -0.40
     Cid
    -0.39
    wp
    -0.38
     even
    -0.38
    POSITIVE LOGITS
    MigrationBuilder
    0.90
     HasFactory
    0.82
    featureID
    0.82
    #+#
    0.81
     ComVisible
    0.80
    
    0.76
    Билгалдахарш
    0.76
    AutoField
    0.72
    ThroughAttribute
    0.69
     henvisninger
    0.67
    Activations Density 1.654%

    No Known Activations