© 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. 33416
    Prev
    Next
    INDEX
    Explanations

    which, why, how

    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
    й
    0.81
    MediaPlayer
    0.80
    ет
    0.79
    к
    0.78
     обнаружи
    0.66
     që
    0.65
    ൺലൈ
    0.65
    '
    0.65
     Bás
    0.64
    ක්
    0.63
    POSITIVE LOGITS
    i
    1.15
    ין
    1.01
    s
    1.01
    in
    0.98
    ان
    0.97
    an
    0.93
    י
    0.93
    e
    0.90
    a
    0.86
    ן
    0.84
    Activations Density 0.033%

    No Known Activations