© 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. 33317
    Prev
    Next
    INDEX
    Explanations

    medical doctor

    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
    a
    0.84
    ia
    0.65
     aguda
    0.62
    ү
    0.62
    LL
    0.60
    Ảnh
    0.60
     확
    0.59
    ored
    0.58
    レット
    0.58
    Κα
    0.58
    POSITIVE LOGITS
    ال
    0.83
    не
    0.76
    ни
    0.75
    ని
    0.66
    ار
    0.66
    بال
    0.64
    <0x91>
    0.64
    ня
    0.63
     Resolutions
    0.62
    ੀ
    0.61
    Activations Density 0.002%

    No Known Activations