© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230038
    Prev
    Next
    INDEX
    Explanations

    plato deliciouso and main dish

    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_6_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
    ห
    1.00
    نا
    0.94
    ים
    0.94
    ח
    0.87
     conveyance
    0.86
    ानी
    0.86
     imbalance
    0.86
     is
    0.84
    ते
    0.80
     equivalence
    0.79
    POSITIVE LOGITS
    at
    1.09
    ó
    1.05
    ut
    1.01
    ot
    1.00
     Puebla
    1.00
    óch
    0.97
     Piem
    0.96
     шесть
    0.95
     Tokugawa
    0.93
    ów
    0.93
    Activations Density 0.000%

    No Known Activations