© 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. 40625
    Prev
    Next
    INDEX
    Explanations

    health education programs

    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
     for
    1.03
    for
    0.82
    a
    0.80
     on
    0.79
    om
    0.69
    ag
    0.68
     by
    0.68
    mist
    0.68
    া
    0.64
    forest
    0.63
    POSITIVE LOGITS
    س
    0.79
    ش
    0.77
    తో
    0.72
    )
    0.66
    ق
    0.66
    كو
    0.62
    ع
    0.60
     Coord
    0.60
    ש
    0.60
     Старки
    0.59
    Activations Density 0.001%

    No Known Activations