© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121894
    Prev
    Next
    INDEX
    Explanations

    Houston Dynamo, Hudson's Bay Company

    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_3_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
    स
    0.81
    us
    0.80
     to
    0.77
    тся
    0.73
    ्यू
    0.70
    هم
    0.69
    ina
    0.68
     and
    0.67
    si
    0.66
    ской
    0.66
    POSITIVE LOGITS
    i
    0.87
    O
    0.72
     Tattha
    0.66
     reorganize
    0.64
    ：
    0.64
    ’
    0.64
     ผม
    0.64
    ヤー
    0.64
     neoplastic
    0.62
    iiv
    0.61
    Activations Density 0.000%

    No Known Activations