© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91969
    Prev
    Next
    INDEX
    Explanations

    Willie Nelson, Whiskey Tango, winner-take-all

    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
    Negative Logits
    ↵↵
    0.81
    ous
    0.77
    ación
    0.76
    al
    0.73
    id
    0.69
    use
    0.65
    Sk
    0.64
    ad
    0.62
    student
    0.61
    sto
    0.61
    POSITIVE LOGITS
    ו
    0.90
    зы
    0.65
    なる
    0.62
    ка
    0.61
    ков
    0.59
    ంగా
    0.59
    و
    0.59
    其他
    0.59
     residencial
    0.59
    л
    0.59
    Activations Density 0.009%

    No Known Activations