© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46350
    Prev
    Next
    INDEX
    Explanations

    air campaign

    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_22_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
    
    0.19
    HO
    0.19
     neighbouring
    0.19
    ibid
    0.18
    hors
    0.18
    Vern
    0.17
    F
    0.17
    atop
    0.17
     पड़
    0.17
     ders
    0.17
    POSITIVE LOGITS
    lage
    0.23
     ഒറ്റ
    0.21
    ⓶
    0.21
     изменения
    0.21
     maroc
    0.20
     merely
    0.20
     unilaterally
    0.20
     monog
    0.20
     برق
    0.20
    Timelapse
    0.20
    Activations Density 0.007%

    No Known Activations