© 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. 85196
    Prev
    Next
    INDEX
    Explanations

    ягід / jad

    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
    d
    1.11
    il
    0.98
    et
    0.95
    '
    0.95
    el
    0.93
    v
    0.93
     is
    0.83
    ↵
    0.77
     Game
    0.75
    b
    0.75
    POSITIVE LOGITS
    us
    0.94
    τή
    0.91
    あり
    0.89
     έχ
    0.86
    ческих
    0.79
    주고
    0.79
    あります
    0.79
    یشه
    0.79
    高く
    0.78
    కు
    0.78
    Activations Density 0.003%

    No Known Activations