© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12075
    Prev
    Next
    INDEX
    Explanations

    be honest with yourself

    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_13_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
    իմ
    0.59
     posiblemente
    0.54
    ーフ
    0.53
     نظام
    0.48
    颖
    0.48
    ional
    0.47
    ープ
    0.47
    ന്റി
    0.47
    ̀nh
    0.47
    úp
    0.46
    POSITIVE LOGITS
    är
    0.58
     outcrop
    0.55
     Если
    0.53
    êmes
    0.50
    Checkbox
    0.50
    roveň
    0.49
     \
    0.49
    צ
    0.49
    Ч
    0.48
     Размер
    0.47
    Activations Density 0.003%

    No Known Activations