© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 67887
    Prev
    Next
    INDEX
    Explanations

    Arabic language

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_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
    mek
    0.43
     mek
    0.42
     ص
    0.41
     č
    0.41
     الكت
    0.41
    દો
    0.40
     مس
    0.40
     taj
    0.40
     amelior
    0.40
     Mek
    0.39
    POSITIVE LOGITS
     N
    0.61
    Est
    0.61
     Est
    0.56
    است
    0.56
     Estes
    0.55
     est
    0.55
    N
    0.55
     الاست
    0.54
     است
    0.54
    Sm
    0.53
    Activations Density 0.002%

    No Known Activations