© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208467
    Prev
    Next
    INDEX
    Explanations

    stadiums or arenas

    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
    Not in Any Lists

    No Comments

    Negative Logits
     slams
    0.39
     ٣
    0.39
    %
    0.39
     destinados
    0.38
     вроде
    0.38
    вро
    0.38
    कर्ताओं
    0.38
     তির
    0.38
     Wann
    0.37
    是否存在
    0.37
    POSITIVE LOGITS
     ওষুধের
    0.41
    astudio
    0.39
     दवा
    0.39
    孀
    0.38
    Ru
    0.37
     Ingredients
    0.37
     Mumbai
    0.37
     낮은
    0.37
    Composer
    0.36
    ruari
    0.36
    Activations Density 0.001%

    No Known Activations