© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2654
    Prev
    Next
    INDEX
    Explanations

    names (both full and partial) of people and places

    oai_token-act-pair · gemini-2.0-flash

    BO

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    RetentionPolicy
    -0.50
     parallel
    -0.49
    uelta
    -0.48
    슷
    -0.48
    <bos>
    -0.48
     puissiez
    -0.47
    jalna
    -0.47
     onData
    -0.46
    reform
    -0.45
    ніципа
    -0.45
    POSITIVE LOGITS
    quiao
    0.75
     boxing
    0.67
    DispatchToProps
    0.65
    __":
    0.59
    Boxing
    0.59
     boxer
    0.59
    ActionCreators
    0.58
    ptonshire
    0.57
     fighters
    0.56
     alphabetically
    0.55
    Activations Density 0.184%

    No Known Activations