© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159455
    Prev
    Next
    INDEX
    Explanations

    Andhra Pradesh, Rivia, Andorra, Andes

    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_2_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
    は
    1.09
    鎗
    1.02
    는
    0.98
     zwei
    0.96
    是
    0.95
     Schwier
    0.95
    ｱ
    0.93
    ഷ്ട്ര
    0.91
    0.91
    
    0.91
    POSITIVE LOGITS
    t
    1.70
    ش
    1.51
    l
    1.50
    ن
    1.42
    ли
    1.41
    the
    1.34
    ع
    1.32
    ed
    1.30
    mr
    1.27
    ت
    1.26
    Activations Density 0.000%

    No Known Activations