© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109886
    Prev
    Next
    INDEX
    Explanations

    портокал

    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_2_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
     be
    0.93
    á
    0.88
    是
    0.84
     (
    0.74
    (
    0.71
    IP
    0.68
    로
    0.66
     è
    0.64
     It
    0.61
    AD
    0.60
    POSITIVE LOGITS
    nosi
    0.74
     پیسې
    0.72
     каче
    0.69
    ﺭ
    0.69
     بیاکت
    0.63
     هیڅ
    0.63
    nThe
    0.63
     وکړئ
    0.62
     гульнявыя
    0.61
    n
    0.60
    Activations Density 0.000%

    No Known Activations