© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9100
    Prev
    Next
    INDEX
    Explanations

    Canada and Canadian

    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_40_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
    িত্ব
    0.40
    etzung
    0.38
    liw
    0.38
     LZ
    0.37
     접
    0.36
     orientale
    0.36
     کولی
    0.36
     nominations
    0.35
     delf
    0.35
    荿
    0.35
    POSITIVE LOGITS
    Canadian
    1.65
     Canadian
    1.61
    Canada
    1.61
     Canada
    1.56
     कनाडा
    1.52
    加拿大
    1.49
    加拿
    1.45
     Canadians
    1.40
    CANADA
    1.39
     Canadá
    1.38
    Activations Density 0.052%

    No Known Activations