© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127595
    Prev
    Next
    INDEX
    Explanations

    Sherbrooke

    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_37_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     બનાવવા
    0.43
     resurrected
    0.41
    ²',
    0.40
     পাচ্ছেন
    0.38
    之为
    0.37
    เมนต์
    0.36
    hesi
    0.35
     lép
    0.35
    梩
    0.35
     faid
    0.34
    POSITIVE LOGITS
    angel
    0.40
    pro
    0.37
    blend
    0.37
    PAPER
    0.37
     deg
    0.37
    pace
    0.36
    focus
    0.36
    good
    0.36
    \{
    0.36
    suggestion
    0.36
    Activations Density 0.000%

    No Known Activations