© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158611
    Prev
    Next
    INDEX
    Explanations

    Mongolian Tugrik

    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_2_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
    一般的
    0.93
    的大
    0.92
    的第一
    0.90
    在那里
    0.89
    一方
    0.88
    一定的
    0.88
    不敢
    0.87
    在
    0.86
    不
    0.85
    在家
    0.84
    POSITIVE LOGITS
    л
    1.52
    ש
    1.45
    ین
    1.44
    v
    1.44
    ル
    1.39
    f
    1.37
    ת
    1.37
    м
    1.33
    ى
    1.28
    ل
    1.27
    Activations Density 0.000%

    No Known Activations