© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84633
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
     for
    2.61
     on
    2.16
    ing
    1.93
    il
    1.63
     a
    1.62
    ig
    1.59
    for
    1.57
     at
    1.51
     in
    1.45
    ik
    1.45
    POSITIVE LOGITS
    ли
    2.06
    ке
    1.77
    ки
    1.57
    dır
    1.53
    <0x80>
    1.52
    нг
    1.48
    ى
    1.47
    ор
    1.46
    き
    1.44
    ви
    1.42
    Activations Density 0.000%

    No Known Activations