© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5446
    Prev
    Next
    INDEX
    Explanations

    Canadian geography and government

    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_44_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
    icrosoft
    0.41
    গ্রেস
    0.41
    ObjData
    0.39
    ังหวัด
    0.37
    SOs
    0.37
    lumat
    0.37
    Objet
    0.37
    僌
    0.36
    rosine
    0.36
    SO
    0.36
    POSITIVE LOGITS
     River
    0.45
    
    0.42
     hsize
    0.39
    Ճ
    0.39
     Да
    0.37
    ͡
    0.37
     Facility
    0.37
    rill
    0.37
    roe
    0.37
    River
    0.36
    Activations Density 0.013%

    No Known Activations