© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208859
    Prev
    Next
    INDEX
    Explanations

    copilot, designer, pro

    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
    됩
    0.19
     Saf
    0.18
    Proto
    0.17
    ចូល
    0.17
    cro
    0.17
     Crop
    0.17
     Becoming
    0.17
    Stock
    0.16
    私
    0.16
    菸
    0.16
    POSITIVE LOGITS
     невозможно
    0.18
     зда
    0.17
     сом
    0.16
     cả
    0.16
    initions
    0.16
     экра
    0.16
     છ
    0.16
     تھے۔
    0.16
     результа
    0.15
     externas
    0.15
    Activations Density 0.003%

    No Known Activations