© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 207957
    Prev
    Next
    INDEX
    Explanations

    comparison of countries

    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_10_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
     countries
    0.82
    Countries
    0.80
     Countries
    0.78
    س
    0.75
    را
    0.74
    ن
    0.71
    وا
    0.64
    度に
    0.63
     países
    0.61
    各国
    0.61
    POSITIVE LOGITS
     mantras
    0.75
     neuroscience
    0.67
     lám
    0.66
     вспом
    0.64
     susah
    0.64
     mantra
    0.63
     ní
    0.63
     tři
    0.61
     helmets
    0.61
     fós
    0.60
    Activations Density 0.012%

    No Known Activations