© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90047
    Prev
    Next
    INDEX
    Explanations

    reach

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    มี
    1.94
     има
    1.27
    有一
    1.22
    需要
    1.20
    有
    1.02
    有一个
    0.94
    有些
    0.93
    จะมี
    0.91
    有一個
    0.91
    有一些
    0.86
    POSITIVE LOGITS
    ่
    0.56
    不行
    0.41
    ໆ
    0.41
     تحقیق
    0.38
    是一些
    0.37
    不多
    0.37
    不对
    0.37
    是一名
    0.37
    不大
    0.36
    <unused43>
    0.35
    Activations Density 0.004%

    No Known Activations