© 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. 47051
    Prev
    Next
    INDEX
    Explanations

    société, society, sociopathy, automation

    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
    Not in Any Lists

    No Comments

    Negative Logits
     i
    0.67
     I
    0.64
     x
    0.64
    もら
    0.63
    و
    0.63
     Sediment
    0.61
     t
    0.60
     свойства
    0.59
     вещества
    0.59
     o
    0.58
    POSITIVE LOGITS
     Société
    1.04
     société
    0.99
     Society
    0.92
    Society
    0.91
    _
    0.91
     società
    0.89
    ک
    0.88
     सोसायटी
    0.85
    ہ
    0.84
    ur
    0.83
    Activations Density 0.000%

    No Known Activations