© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62828
    Prev
    Next
    INDEX
    Explanations

    Eis, Baum, Wahl

    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_2_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
    ни
    1.17
    is
    1.11
     I
    1.05
    ти
    0.99
    <0x0D>
    0.99
    ha
    0.98
     (
    0.96
    il
    0.90
    hi
    0.90
    de
    0.89
    POSITIVE LOGITS
    می
    1.13
    ك
    1.09
    مر
    1.05
    د
    1.04
    اً
    1.03
    س
    1.03
    اق
    1.02
    க்
    0.97
    、
    0.93
    ए
    0.92
    Activations Density 0.001%

    No Known Activations