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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33996
    Prev
    Next
    INDEX
    Explanations

    latest developments

    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_31_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
    徹
    0.33
     지금
    0.33
     جديدة
    0.33
     दश
    0.30
    卆
    0.30
    તન
    0.29
    현재
    0.29
     받을
    0.29
    automate
    0.29
    documentation
    0.28
    POSITIVE LOGITS
     geography
    0.28
     मार्गों
    0.28
     Geography
    0.28
     qw
    0.28
     हों
    0.27
     %>%
    0.27
     गे
    0.27
     także
    0.27
    人们
    0.27
     gevol
    0.27
    Activations Density 0.004%

    No Known Activations