© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205564
    Prev
    Next
    INDEX
    Explanations

    import uno, Image, Translate

    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_20_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
     інших
    0.28
     drugih
    0.28
    ਾਰ
    0.25
     다른
    0.25
    është
    0.24
    онів
    0.24
    髅
    0.24
     другими
    0.24
     പിന്തുണ
    0.24
     advices
    0.24
    POSITIVE LOGITS
    ?
    0.34
    ...
    0.26
    大きな
    0.25
    ประ
    0.25
    業者
    0.25
     জায়গায়
    0.24
     blender
    0.24
    Хо
    0.24
     kesulitan
    0.23
     Mateo
    0.23
    Activations Density 0.000%

    No Known Activations