© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162657
    Prev
    Next
    INDEX
    Explanations

    dehumanizing others

    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_2_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
    1.50
     it
    1.29
     It
    1.26
    н
    1.24
     as
    1.21
    น
    1.20
    й
    1.16
    ن
    1.16
     For
    1.14
     inférieure
    1.12
    POSITIVE LOGITS
    3
    1.56
    2
    1.55
    5
    1.48
    (
    1.34
    6
    1.30
    -
    1.27
    ون
    1.24
    4
    1.13
    ంగా
    0.98
    9
    0.95
    Activations Density 0.001%

    No Known Activations