© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9370
    Prev
    Next
    INDEX
    Explanations

    Latex markup and mathematical expressions.

    oai_token-act-pair · gemini-2.0-flash

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     random
    -0.84
     randomly
    -0.67
    random
    -0.66
    Random
    -0.65
     Random
    -0.58
     RANDOM
    -0.50
     individual
    -0.48
    fällig
    -0.47
    getClass
    -0.46
    حياته
    -0.46
    POSITIVE LOGITS
    UnusedPrivate
    0.85
     betweenstory
    0.85
    WriteLiteral
    0.79
     Paglinawan
    0.78
    endphp
    0.77
     kaarangay
    0.74
     initComponents
    0.71
     nahilalakip
    0.71
    HomeAsUpEnabled
    0.69
    تقاوى
    0.68
    Activations Density 18.914%

    No Known Activations