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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12243
    Prev
    Next
    INDEX
    Explanations

    names of people, especially those involved in legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    court cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -0.54
    ărul
    -0.50
     Selva
    -0.47
    zkod
    -0.46
    masan
    -0.45
     Schilder
    -0.44
     Crock
    -0.43
     schle
    -0.43
     Salad
    -0.42
     informée
    -0.42
    POSITIVE LOGITS
    AndEndTag
    0.72
    setVerticalGroup
    0.63
    SequentialGroup
    0.61
    nonatomic
    0.59
    providedIn
    0.57
     CURIAM
    0.56
    RenderAtEndOf
    0.55
     InputDecoration
    0.54
    ActionTypes
    0.54
    ---|---|
    0.54
    Activations Density 3.112%

    No Known Activations