© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37934
    Prev
    Next
    INDEX
    Explanations

    результат

    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_11_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
    ب
    0.61
    ológicos
    0.58
    6
    0.58
    h
    0.55
    ۷
    0.55
    fans
    0.54
    n
    0.54
    ज
    0.54
    ia
    0.54
    ah
    0.53
    POSITIVE LOGITS
    ጳ
    0.66
     quelconque
    0.62
     kinases
    0.61
     purus
    0.58
     entsteht
    0.55
    腃
    0.55
     puris
    0.55
     stoves
    0.54
    يذ
    0.54
     tempus
    0.54
    Activations Density 0.001%

    No Known Activations