© 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. 12091
    Prev
    Next
    INDEX
    Explanations

    more, further, additional

    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
    leaders
    0.66
    as
    0.66
    ید
    0.63
    chronic
    0.63
    another
    0.63
    یر
    0.61
    a
    0.61
    )=\
    0.60
    یس
    0.60
     Synd
    0.60
    POSITIVE LOGITS
     robust
    0.60
     ribs
    0.57
     коре
    0.57
     широкий
    0.54
     것처럼
    0.53
     М
    0.53
    เซล
    0.52
     breasts
    0.52
     отсутствие
    0.51
     прости
    0.51
    Activations Density 0.000%

    No Known Activations