© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27905
    Prev
    Next
    INDEX
    Explanations

    bidi control character

    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_10_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
     to
    0.88
    ,
    0.83
    يت
    0.82
    ви
    0.77
     are
    0.76
    ى
    0.75
     itse
    0.70
    ă
    0.70
     can
    0.69
    ак
    0.68
    POSITIVE LOGITS
    емые
    0.71
     léč
    0.68
    riterion
    0.68
     Более
    0.68
     Работа
    0.66
    י
    0.66
     mensuales
    0.64
     Pokud
    0.63
     شهید
    0.63
     Dlatego
    0.63
    Activations Density 0.000%

    No Known Activations