© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5647
    Prev
    Next
    INDEX
    Explanations

    中文与英文混合

    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_38_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
    將
    0.77
    将
    0.73
    把
    0.71
     将
    0.69
     將
    0.68
    把他
    0.67
    将其
    0.66
     把
    0.61
    把我
    0.61
    就把
    0.59
    POSITIVE LOGITS
    展现
    0.37
     повинні
    0.36
    मिशन
    0.35
    פּ
    0.35
    ｏ
    0.35
     Transitions
    0.33
    Mind
    0.33
     concernant
    0.32
     সৈনিক
    0.32
    боли
    0.32
    Activations Density 0.026%

    No Known Activations