© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 200095
    Prev
    Next
    INDEX
    Explanations

    same sex

    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_9_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
     \
    0.44
     $
    0.35
     a
    0.34
     anesthesia
    0.31
     pajamas
    0.30
     storage
    0.30
     $\
    0.29
     question
    0.29
    还
    0.28
    后
    0.28
    POSITIVE LOGITS
    is
    0.55
    '
    0.53
    it
    0.43
    ’
    0.39
    n
    0.39
    j
    0.37
    id
    0.37
     Bericht
    0.36
    i
    0.36
    isjon
    0.36
    Activations Density 0.015%

    No Known Activations