© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39891
    Prev
    Next
    INDEX
    Explanations

    autoexec, autopista, automattic, autopsy, translator

    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_3_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
    其他
    0.82
    ;
    0.60
     preclude
    0.59
     jungen
    0.58
     festgelegt
    0.57
    🥅
    0.57
     erfol
    0.56
    时间和
    0.55
     strokeWeight
    0.54
    }());
    0.54
    POSITIVE LOGITS
    to
    1.00
    et
    0.87
    t
    0.85
    m
    0.85
    م
    0.80
    ت
    0.79
    of
    0.76
    may
    0.71
    at
    0.70
    is
    0.70
    Activations Density 0.004%

    No Known Activations