© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36215
    Prev
    Next
    INDEX
    Explanations

    province

    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
     integrator
    0.38
    酮
    0.37
    .|__
    0.37
     ডিফ
    0.37
    constexpr
    0.36
     pellet
    0.36
    𝚍
    0.36
     elk
    0.34
     thermodynamic
    0.34
     ব্যক্তিত্ব
    0.34
    POSITIVE LOGITS
     province
    2.27
     Province
    2.14
    province
    2.14
    Province
    2.13
     provinces
    2.06
     provinsi
    2.06
    省
    2.06
     provincia
    2.03
     провин
    1.94
     Provinces
    1.91
    Activations Density 0.060%

    No Known Activations