© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54908
    Prev
    Next
    INDEX
    Explanations

    processing

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    mixing
    0.39
     register
    0.38
     Официа
    0.38
     ಇನ್ನ
    0.38
    Register
    0.37
    следование
    0.37
     Register
    0.37
     mixing
    0.37
     urination
    0.37
    乨
    0.37
    POSITIVE LOGITS
     Processing
    0.54
     processing
    0.51
     process
    0.49
    process
    0.49
     grace
    0.48
     süreç
    0.48
    processed
    0.46
     processed
    0.45
    Processing
    0.45
     PROCESSING
    0.45
    Activations Density 0.045%

    No Known Activations