© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 214803
    Prev
    Next
    INDEX
    Explanations

    contrasting pairs or opposites

    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_31_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
     трех
    0.42
     ዓይነት
    0.39
     Pem
    0.38
     Classics
    0.38
     af
    0.37
     ક્ર
    0.36
    丨
    0.36
     î
    0.36
     चीन
    0.35
     कोय
    0.35
    POSITIVE LOGITS
     versus
    0.67
    versus
    0.55
    vs
    0.55
     instead
    0.54
     Versus
    0.54
    Conversely
    0.54
    逆に
    0.51
     rather
    0.51
     conversely
    0.50
    instead
    0.50
    Activations Density 0.059%

    No Known Activations