© 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. 92351
    Prev
    Next
    INDEX
    Explanations

    really do! or did!

    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
     on
    0.75
    a
    0.71
    i
    0.68
    on
    0.65
    ,
    0.62
     as
    0.55
    ;
    0.55
    :
    0.55
     where
    0.54
    ה
    0.54
    POSITIVE LOGITS
     системы
    0.68
     городского
    0.66
     системой
    0.64
     каждого
    0.60
     использования
    0.57
     государство
    0.55
     তাহাদের
    0.55
     большинства
    0.55
     ተመሳሳይ
    0.54
     اہلِ
    0.54
    Activations Density 0.012%

    No Known Activations