© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165065
    Prev
    Next
    INDEX
    Explanations

    Southeast Asian 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_31_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
     grow
    0.37
    xlabel
    0.36
    $%
    0.36
    abbage
    0.36
     hacerse
    0.34
    wbr
    0.34
    ष्य
    0.33
     nebul
    0.33
     cfg
    0.33
     मजबूर
    0.32
    POSITIVE LOGITS
     کشورهای
    0.45
     Afghanistan
    0.44
     Malaysia
    0.43
    COUNTRIES
    0.43
     Indonesia
    0.42
    ("[
    0.41
     Vietnam
    0.40
     countries
    0.39
     Africa
    0.39
     Demographic
    0.39
    Activations Density 0.003%

    No Known Activations