© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 206905
    Prev
    Next
    INDEX
    Explanations

    main focus

    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_6_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
    ク
    1.02
    اء
    0.97
    у
    0.97
    च
    0.95
    द
    0.93
    ۵
    0.92
    ме
    0.91
    ন
    0.89
    ض
    0.88
    이다
    0.86
    POSITIVE LOGITS
    t
    1.27
    '
    1.05
     are
    0.89
    have
    0.84
    v
    0.83
    "
    0.83
    ror
    0.77
    For
    0.76
     og
    0.75
     objects
    0.73
    Activations Density 0.002%

    No Known Activations