© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4818
    Prev
    Next
    INDEX
    Explanations

    HTML tags and content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    য়র
    1.64
    и
    1.62
    紝
    1.47
     سبيل
    1.47
    $-\
    1.45
    bm
    1.44
    хождение
    1.44
    য়ে
    1.43
     anticipation
    1.40
     QtCore
    1.40
    POSITIVE LOGITS
    an
    2.04
    ларга
    1.97
    resistant
    1.96
    و
    1.88
     башка
    1.87
    ो
    1.78
    rewrite
    1.71
     kinship
    1.71
    此之外
    1.70
    ಿ
    1.67
    Activations Density 0.001%

    No Known Activations