© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5830
    Prev
    Next
    INDEX
    Explanations

    words related to artistic or athletic performances and related actions

    oai_token-act-pair · gemini-2.0-flash

    performance

    np_max-act · gemini-2.0-flash

    performance

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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>
    -0.71
    *
    -0.54
    (
    -0.51
    To
    -0.47
    #
    -0.47
    Google
    -0.46
    <h2>
    -0.46
    "
    -0.46
    //
    -0.45
    This
    -0.44
    POSITIVE LOGITS
    setVerticalGroup
    0.95
    ScopeManager
    0.85
    PickerController
    0.77
    曖昧さ回避
    0.75
    enumii
    0.73
     للمعارف
    0.73
    RectangleBorder
    0.72
    beelden
    0.70
    houding
    0.69
     HttpNotFound
    0.69
    Activations Density 0.402%

    No Known Activations