© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78279
    Prev
    Next
    INDEX
    Explanations

    idiom or idiocy

    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_0_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
    ı
    1.55
     élarg
    1.50
    한
    1.47
    어
    1.45
     étroit
    1.43
    ని
    1.41
    스
    1.41
     όχι
    1.41
     equilibrio
    1.39
     thời
    1.38
    POSITIVE LOGITS
    an
    1.84
    ان
    1.74
    t
    1.74
    tte
    1.37
    ed
    1.34
     you
    1.34
    ts
    1.30
    gende
    1.30
    ر
    1.27
    tes
    1.26
    Activations Density 0.000%

    No Known Activations