© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13238
    Prev
    Next
    INDEX
    Explanations

    lie detector

    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_15_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
     Балтбет
    0.55
    š
    0.53
     Aladdin
    0.52
    »).
    0.51
    꼫
    0.50
    argon
    0.50
    turbo
    0.50
    chod
    0.50
    COMMIT
    0.49
    च
    0.48
    POSITIVE LOGITS
    ↵↵
    0.55
     depl
    0.54
     brothers
    0.46
     دنبال
    0.45
      
    0.43
     guardianship
    0.43
    ’
    0.43
     siblings
    0.42
     exuber
    0.42
     sisters
    0.42
    Activations Density 0.005%

    No Known Activations