© 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. 85411
    Prev
    Next
    INDEX
    Explanations

    website

    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
    یت
    0.76
    <0x0D>
    0.72
     to
    0.64
    ä
    0.64
     of
    0.64
    ！
    0.63
    \}=
    0.63
    یس
    0.61
    する
    0.60
    \
    0.57
    POSITIVE LOGITS
    t
    0.66
    i
    0.66
    ت
    0.65
    r
    0.60
    ed
    0.60
    læ
    0.54
    nahme
    0.54
    zunehmen
    0.52
    ið
    0.52
    njih
    0.52
    Activations Density 0.003%

    No Known Activations