© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59197
    Prev
    Next
    INDEX
    Explanations

    How to, who has, what would

    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_11_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
     hochwert
    0.51
     zwölf
    0.47
     guida
    0.47
    ("%
    0.46
     świat
    0.46
     aceasta
    0.45
     mū
    0.45
     எண்
    0.45
     privind
    0.44
     irmã
    0.44
    POSITIVE LOGITS
    ت
    0.50
    oles
    0.46
    asar
    0.46
     ਨਾਲ
    0.45
    alar
    0.45
    elen
    0.45
     الاس
    0.43
     scrapes
    0.42
    ware
    0.42
    ிக
    0.42
    Activations Density 0.003%

    No Known Activations