© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3894
    Prev
    Next
    INDEX
    Explanations

    code syntax, especially square and curly brackets, parenthesis, and certain keywords like function and directive

    oai_token-act-pair · gemini-2.0-flash

    brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     [
    -0.55
     rato
    -0.51
    drawSprites
    -0.50
    Ữ
    -0.48
     partners
    -0.48
    =[
    -0.47
     band
    -0.47
     partner
    -0.47
    umab
    -0.46
    inburgh
    -0.46
    POSITIVE LOGITS
    TagMode
    0.82
    AddHtmlAttribute
    0.81
    RenderAtEndOf
    0.77
    setVerticalGroup
    0.74
     betweenstory
    0.72
     насељу
    0.67
    <bos>
    0.67
    WebServlet
    0.65
    OGND
    0.63
    AutoScale
    0.62
    Activations Density 4.011%

    No Known Activations