© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 212567
    Prev
    Next
    INDEX
    Explanations

    seriously?

    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_19_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
    ake
    0.44
     Japanese
    0.43
    ı
    0.42
     objekt
    0.38
     Witch
    0.38
     Objet
    0.38
     Biochem
    0.37
     Japan
    0.37
    ‌ని
    0.37
    ignment
    0.37
    POSITIVE LOGITS
     भला
    0.49
     nemo
    0.47
     utilizzare
    0.47
    Restaurants
    0.46
     ristor
    0.46
     ਬ
    0.45
    昨日
    0.44
    হত্যা
    0.44
    龰
    0.44
    靂
    0.43
    Activations Density 0.002%

    No Known Activations