© 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. 215942
    Prev
    Next
    INDEX
    Explanations

    limited

    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
    ской
    1.27
     as
    1.26
    ם
    1.26
    ছে
    1.20
    ालय
    1.20
    ためには
    1.17
    ように
    1.13
    gunaan
    1.13
    $.
    1.13
    ために
    1.13
    POSITIVE LOGITS
    on
    1.41
     on
    1.34
     for
    1.33
    م
    1.32
    os
    1.27
    ian
    1.19
    ats
    1.18
    ي
    1.18
    ion
    1.16
    ி
    1.16
    Activations Density 0.000%

    No Known Activations