© 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. 129036
    Prev
    Next
    INDEX
    Explanations

    let him

    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
    .
    1.16
    iz
    1.07
    ig
    0.97
    ims
    0.93
    on
    0.87
    em
    0.84
    ات
    0.84
    ogens
    0.83
    iv
    0.80
    ots
    0.80
    POSITIVE LOGITS
    ל
    1.27
    ור
    1.27
     DUI
    1.13
     Ș
    1.12
     ș
    1.06
    ру
    1.05
     an
    1.01
    the
    1.01
    A
    0.98
     Ā
    0.95
    Activations Density 0.003%

    No Known Activations