© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8310
    Prev
    Next
    INDEX
    Explanations

    punctuation and short function words, such as coordinating conjunctions and prepositions

    oai_token-act-pair · gemini-2.0-flash

    Code and legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     marketplace
    -0.41
    establishing
    -0.40
     Spra
    -0.40
    ngx
    -0.39
    ganta
    -0.39
    ėtų
    -0.38
     uz
    -0.38
     uch
    -0.37
    EST
    -0.37
     vàng
    -0.36
    POSITIVE LOGITS
     AssemblyProduct
    0.81
    iastes
    0.79
    WebVitals
    0.79
    typeorm
    0.72
    جغرافيا
    0.70
    withIdentifier
    0.68
     '+':
    0.67
    NewUrlParser
    0.66
    WebpackPlugin
    0.66
    RectangleBorder
    0.66
    Activations Density 1.106%

    No Known Activations