© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58315
    Prev
    Next
    INDEX
    Explanations

    society, nation, language

    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_59_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
    мента
    0.52
    нику
    0.50
    מו
    0.49
    ټر
    0.48
    ښ
    0.46
    В
    0.45
    вор
    0.45
     whirling
    0.45
    им
    0.44
     saya
    0.43
    POSITIVE LOGITS
     визнача
    0.66
     са
    0.63
     определя
    0.61
     державних
    0.60
     обществе
    0.58
     사
    0.58
     городов
    0.58
     цих
    0.55
     городах
    0.54
     країн
    0.54
    Activations Density 0.003%

    No Known Activations