© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13671
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names of sports teams, car models, legal documents and websites

    oai_token-act-pair · gemini-2.0-flash

    United States legal context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Wikipedia
    -0.54
    ropia
    -0.49
    ⓘ
    -0.49
     Wiki
    -0.48
     Ma
    -0.48
    ayi
    -0.47
    omite
    -0.47
    <tbody>
    -0.47
     setValue
    -0.47
    weilen
    -0.47
    POSITIVE LOGITS
     дописавши
    1.09
     NSCoder
    0.98
    +#+#
    0.88
    TypedDataSet
    0.78
    RegressionTest
    0.77
    ніципалі
    0.74
     للمعارف
    0.72
     <=",
    0.72
     "..\..\..\
    0.72
     ModelExpression
    0.72
    Activations Density 6.181%

    No Known Activations