© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35857
    Prev
    Next
    INDEX
    Explanations

    foreign words and word parts

    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_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
    ЗА
    0.75
    のリ
    0.73
    کرات
    0.73
    時の
    0.72
    ک
    0.71
    𝒌
    0.70
    おすすめ
    0.69
    کز
    0.69
    کریاں
    0.67
    Ни
    0.67
    POSITIVE LOGITS
    t
    1.27
    al
    1.06
    c
    1.00
    d
    0.98
    v
    0.88
    ad
    0.87
    y
    0.86
    p
    0.83
    l
    0.81
    x
    0.80
    Activations Density 0.002%

    No Known Activations