© 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. 9193
    Prev
    Next
    INDEX
    Explanations

    words related to processes, often in a scientific context

    oai_token-act-pair · gemini-2.0-flash

    scientific text

    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
    <bos>
    -0.83
     Administrativna
    -0.68
     الحره
    -0.67
    SequentialGroup
    -0.66
    GOTREF
    -0.65
    ViewImports
    -0.63
    UVWXYZ
    -0.63
    AccessorTable
    -0.58
    IsMutable
    -0.58
     Paglinawan
    -0.57
    POSITIVE LOGITS
    
    0.59
     resourceCulture
    0.57
    WriteLiteral
    0.55
     OFDb
    0.55
    UnitTesting
    0.54
     surla
    0.53
    emptions
    0.50
     opérateur
    0.49
    getKeyCode
    0.46
    }}]{
    0.46
    Activations Density 1.711%

    No Known Activations