© 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. 176642
    Prev
    Next
    INDEX
    Explanations

    services communicate with each other

    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
     calomel
    0.50
     нейтро
    0.48
     РАН
    0.48
     Рос
    0.48
    _{\{
    0.47
     diphenyl
    0.46
     configs
    0.45
     серии
    0.45
     supersymmetric
    0.45
     erode
    0.45
    POSITIVE LOGITS
     S
    0.49
     There
    0.48
    Market
    0.46
     Business
    0.46
     Act
    0.46
     At
    0.45
    ↵↵↵↵↵
    0.45
    S
    0.44
    Too
    0.44
    Up
    0.43
    Activations Density 0.004%

    No Known Activations