© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33294
    Prev
    Next
    INDEX
    Explanations

    Urdu and Hindi sentences

    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_50_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
     کو
    0.51
     ko
    0.51
    コ
    0.51
    ko
    0.49
    كو
    0.49
     KO
    0.48
    KO
    0.46
    Ko
    0.45
     tak
    0.44
     Ko
    0.44
    POSITIVE LOGITS
    Ky
    0.45
     Ky
    0.39
    スケ
    0.39
    rake
    0.38
     feast
    0.38
    চ্
    0.38
    рки
    0.37
    iske
    0.37
    겠
    0.37
    ന്നി
    0.36
    Activations Density 0.005%

    No Known Activations