© 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-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39360
    Prev
    Next
    INDEX
    Explanations

    feathered animals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bär
    0.54
    "،
    0.50
    <0x99>
    0.49
    '";
    0.49
     ă
    0.49
    ?".
    0.49
    TableName
    0.49
     Shabb
    0.48
    ㅍ
    0.48
    ﺽ
    0.47
    POSITIVE LOGITS
     leverages
    0.51
     independ
    0.50
     leveraged
    0.50
    制
    0.50
    radio
    0.50
     indépend
    0.49
     Leverage
    0.48
     zuvor
    0.46
    Dynam
    0.46
     jì
    0.46
    Activations Density 0.028%

    No Known Activations