© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88865
    Prev
    Next
    INDEX
    Explanations

    absolutism or absolute

    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_3_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
    тна
    0.86
    ካከል
    0.86
     Гинд
    0.79
     போக்குவர
    0.70
     Америка
    0.69
    둴
    0.69
    ვის
    0.68
    кта
    0.68
    ნი
    0.67
     История
    0.67
    POSITIVE LOGITS
    ;
    1.12
    *
    0.96
    ot
    0.96
    é
    0.90
    ó
    0.90
    o
    0.89
    of
    0.88
    ed
    0.88
     of
    0.85
    ol
    0.84
    Activations Density 0.003%

    No Known Activations