© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200281
    Prev
    Next
    INDEX
    Explanations

    therapy

    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_6_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
    ä
    1.97
    '
    1.56
    \
    1.42
    et
    1.38
     was
    1.25
    B
    1.19
     be
    1.18
     It
    1.17
    au
    1.13
    IT
    1.11
    POSITIVE LOGITS
    denoted
    0.98
    thed
    0.97
    も含
    0.95
    かかる
    0.93
    familyName
    0.91
    =".
    0.91
    kyt
    0.90
     Счетчик
    0.90
    cdot
    0.89
     الغذ
    0.88
    Activations Density 0.000%

    No Known Activations