© 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. 33270
    Prev
    Next
    INDEX
    Explanations

    signal processing steps

    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
    IR
    0.66
     for
    0.64
    
    0.60
    for
    0.59
     Moldova
    0.59
    滙
    0.59
     the
    0.58
    CT
    0.57
    that
    0.57
    $+
    0.57
    POSITIVE LOGITS
    ה
    0.80
    ной
    0.77
    ס
    0.77
    ما
    0.75
    ي
    0.73
    ין
    0.70
    ное
    0.69
    ین
    0.66
    も
    0.65
    ция
    0.63
    Activations Density 0.002%

    No Known Activations