© 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. 85401
    Prev
    Next
    INDEX
    Explanations

    likely or want

    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
    с
    0.87
    ห
    0.81
    บ
    0.78
    ть
    0.76
    ท
    0.74
    ต
    0.72
     are
    0.71
    น
    0.71
    ן
    0.70
     powied
    0.69
    POSITIVE LOGITS
    i
    1.02
    k
    0.97
    ed
    0.86
    b
    0.86
    ið
    0.84
    ER
    0.83
    iencia
    0.83
    kungan
    0.78
     slalom
    0.77
    ième
    0.75
    Activations Density 0.000%

    No Known Activations