© 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. 11738
    Prev
    Next
    INDEX
    Explanations

    heterogeneous architectures, systems, electronics, hardware

    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
     Теперь
    0.59
    🥛
    0.56
     беспо
    0.55
     используется
    0.54
     ходить
    0.54
    zeit
    0.54
     sinds
    0.53
     वापर
    0.52
    znál
    0.52
     জন্যই
    0.52
    POSITIVE LOGITS
     aren
    0.61
     rental
    0.57
     N
    0.57
     tr
    0.56
     caricature
    0.55
     truc
    0.54
     c
    0.53
     hull
    0.53
     scratch
    0.53
     dramatic
    0.52
    Activations Density 0.033%

    No Known Activations