© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44286
    Prev
    Next
    INDEX
    Explanations

    study by

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ldes
    0.45
     एगो
    0.45
    ogliere
    0.45
     trail
    0.43
    㧿
    0.43
     anton
    0.42
     متغير
    0.42
     créé
    0.42
     enero
    0.41
     lows
    0.41
    POSITIVE LOGITS
    Row
    0.45
      
    0.39
     Smo
    0.39
     Ski
    0.38
    ’
    0.37
    Chrom
    0.37
     Survey
    0.37
    Warehouse
    0.37
    縣
    0.37
     কেন্দ্রীয়
    0.36
    Activations Density 0.001%

    No Known Activations