© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21903
    Prev
    Next
    INDEX
    Explanations

    Бу

    np_max-act-logits · gemini-2.5-flash-lite

    words starting with "бу".

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @enricobottazzi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     Hamlin
    0.38
    含
    0.36
    ментов
    0.35
    zeniu
    0.35
     vuccanti
    0.35
    ংস
    0.34
    வில
    0.34
    㐸
    0.33
    uencia
    0.33
    学习
    0.33
    POSITIVE LOGITS
    有所
    0.53
    有一些
    0.50
    有
    0.50
    着
    0.48
    有一
    0.47
    有一個
    0.46
    착
    0.43
    有一个
    0.43
     има
    0.42
     có
    0.41
    Activations Density 0.000%

    No Known Activations