© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7487
    Prev
    Next
    INDEX
    Explanations

    words that appear in legal documents, especially associated with court cases

    oai_token-act-pair · gemini-2.0-flash

    Contains "self" or "ſ"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    omitempty
    -0.65
    walde
    -0.63
     para
    -0.63
    knecht
    -0.60
     Kon
    -0.59
      (
    -0.58
    tvguidetime
    -0.58
     mad
    -0.57
    bidden
    -0.57
     co
    -0.55
    POSITIVE LOGITS
     itſelf
    0.97
     Anſ
    0.75
    ſelves
    0.73
     auffi
    0.71
     ་་
    0.69
     unſ
    0.66
    <bos>
    0.65
    ſelf
    0.62
     themſelves
    0.62
     Houſe
    0.60
    Activations Density 17.134%

    No Known Activations