© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81712
    Prev
    Next
    INDEX
    Explanations

    digits

    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_0_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
    ي
    2.72
    י
    2.59
    i
    2.28
    ה
    2.27
    ق
    2.23
    is
    2.11
    م
    2.11
    ت
    2.09
    מ
    2.03
    ب
    1.91
    POSITIVE LOGITS
     bruge
    1.27
     Bedeutung
    1.16
    ě
    1.14
     revisión
    1.09
     Mandarin
    1.04
     forgo
    1.04
     doit
    1.02
     transact
    1.02
     Vergangenheit
    1.01
     manutenção
    0.97
    Activations Density 0.001%

    No Known Activations