© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 238432
    Prev
    Next
    INDEX
    Explanations

    negation or absence

    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_32_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
     inactive
    0.50
    不安定
    0.49
     unsatisf
    0.48
     unstable
    0.47
     ineffective
    0.47
     inaccurate
    0.46
     inactivity
    0.46
     incom
    0.45
    不
    0.45
     insecurity
    0.44
    POSITIVE LOGITS
    熏
    0.39
    ไซ
    0.37
     امرأة
    0.37
     raport
    0.37
    송
    0.37
    报告
    0.35
     picnics
    0.35
     REPORTS
    0.35
     sj
    0.34
     различи
    0.34
    Activations Density 0.054%

    No Known Activations