© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4837
    Prev
    Next
    INDEX
    Explanations

    a word "part" followed by something and words that mentions scales and numbers

    oai_token-act-pair · gemini-2.0-flash

    verbs, especially "-ing" words

    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
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.51
    ;">
    -0.50
     Bestandteil
    -0.49
    %");
    -0.49
     boku
    -0.49
    brada
    -0.47
    OVERY
    -0.47
    StateToProps
    -0.47
     acuer
    -0.47
     ")
    -0.47
    POSITIVE LOGITS
     ویکی‌پدیا
    0.71
    Rüyada
    0.65
     مرئيه
    0.63
    tangentMode
    0.62
     HasFactory
    0.61
    posób
    0.58
    fjspx
    0.57
    allero
    0.56
    loài
    0.55
    AutoScaleMode
    0.55
    Activations Density 1.793%

    No Known Activations