© 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. 33298
    Prev
    Next
    INDEX
    Explanations

    capturing

    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
    ו
    1.06
    I
    0.89
    il
    0.87
    ,
    0.75
    ol
    0.74
    al
    0.73
    و
    0.72
    T
    0.66
    W
    0.65
    Christ
    0.63
    POSITIVE LOGITS
     capturing
    0.81
    리
    0.79
     Capture
    0.79
    ết
    0.75
     capture
    0.73
     cáps
    0.72
    ít
    0.70
     कब्जा
    0.67
    코드
    0.67
     captured
    0.66
    Activations Density 0.008%

    No Known Activations