© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211939
    Prev
    Next
    INDEX
    Explanations

    indians and indígenas

    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_5_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
    ر
    1.59
    ي
    1.59
    ش
    1.55
    u
    1.52
    r
    1.46
    و
    1.45
    i
    1.45
    기
    1.41
    ز
    1.39
    р
    1.38
    POSITIVE LOGITS
     on
    1.33
    IAN
    1.13
    IM
    1.04
     appartient
    1.02
    的相关
    1.01
    alaikums
    1.01
    的游戏
    0.99
    IC
    0.98
    的关系
    0.96
    的服务
    0.96
    Activations Density 0.002%

    No Known Activations