© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36346
    Prev
    Next
    INDEX
    Explanations

    NCR and North India locations

    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_11_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
    et
    0.86
    in
    0.77
    ak
    0.67
    ar
    0.64
    y
    0.63
    ad
    0.59
    es
    0.58
    ent
    0.57
    est
    0.57
     drilled
    0.57
    POSITIVE LOGITS
     productividad
    0.62
    خذ
    0.61
    점
    0.60
    بی
    0.57
     Liberties
    0.56
    Ordine
    0.56
    な
    0.55
    یند
    0.54
    Document
    0.54
     ایمان
    0.54
    Activations Density 0.000%

    No Known Activations