© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142350
    Prev
    Next
    INDEX
    Explanations

    expectations

    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_12_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
    are
    0.66
    I
    0.64
    Are
    0.64
    t
    0.64
    E
    0.63
    ro
    0.63
    your
    0.62
    Health
    0.61
    how
    0.60
     את
    0.59
    POSITIVE LOGITS
    SegmentInfo
    0.59
    GONDOR
    0.58
     klima
    0.58
    لمانيا
    0.55
    мата
    0.54
     مشہور
    0.54
    Ѡ
    0.54
     داشت
    0.54
     Selon
    0.54
    тельном
    0.54
    Activations Density 0.005%

    No Known Activations