© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50487
    Prev
    Next
    INDEX
    Explanations

    france and French

    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_30_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
     Istituto
    0.43
    Instituto
    0.42
    )}{\
    0.40
     finca
    0.40
     függ
    0.39
     Instituto
    0.39
    datos
    0.39
    }}{\
    0.39
    academia
    0.38
     Hacienda
    0.38
    POSITIVE LOGITS
     France
    0.61
     Франция
    0.60
     Frankreich
    0.58
    フランス
    0.58
     French
    0.55
    France
    0.55
     france
    0.55
     францу
    0.54
     الفرنس
    0.54
     فرنسا
    0.53
    Activations Density 0.007%

    No Known Activations