© 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. 218325
    Prev
    Next
    INDEX
    Explanations

    UI element classes (modal, carousel, card, text)

    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
     Гра
    0.29
     demonstrated
    0.29
     возра
    0.29
     evidencia
    0.29
     Standing
    0.28
    laughter
    0.28
     अद्वितीय
    0.27
     \%(
    0.27
    ੌਰ
    0.27
     Ideally
    0.27
    POSITIVE LOGITS
    西洋
    0.29
     الجزائر
    0.28
    इंडियन
    0.28
    合わせ
    0.28
    svc
    0.28
     SVC
    0.27
     الفلسط
    0.27
     başlayan
    0.27
    ègues
    0.27
    anyol
    0.27
    Activations Density 0.000%

    No Known Activations