© 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. 7206
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to different knowledge domains, including software, law, medicine, and potentially others, and also finds some XML markup

    oai_token-act-pair · gemini-2.0-flash

    Legal/medical arguments

    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
    IntoConstraints
    -0.78
    Personendaten
    -0.73
    ren
    -0.68
    出版年
    -0.68
    ActionCreators
    -0.68
    DoubleQuotes
    -0.67
    ven
    -0.65
    UpInside
    -0.64
    REN
    -0.59
    VEN
    -0.57
    POSITIVE LOGITS
    こち
    0.55
    psies
    0.50
     समीक्षक
    0.49
     상세
    0.48
    aume
    0.48
    kort
    0.46
    లాలు
    0.46
    Архівовано
    0.45
    ⏜
    0.44
     Hö
    0.43
    Activations Density 13.089%

    No Known Activations