© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209564
    Prev
    Next
    INDEX
    Explanations

    Riverpod providers or book clubs

    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_5_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
    stas
    1.01
     améliorer
    0.92
     Susana
    0.89
    ТЕ
    0.89
    来
    0.88
    كة
    0.87
    器的
    0.87
     одежды
    0.87
    彠
    0.86
     определя
    0.85
    POSITIVE LOGITS
    on
    1.31
    ?
    1.30
    i
    1.23
    ো
    1.20
    an
    1.20
    iin
    1.19
    л
    1.16
    il
    1.10
    ן
    1.09
    res
    1.09
    Activations Density 0.000%

    No Known Activations