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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261425
    Prev
    Next
    INDEX
    Explanations

    **raw** beef liver

    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
    ین
    1.69
    لی
    1.57
    st
    1.46
    ק
    1.41
    سی
    1.38
    л
    1.37
    н
    1.32
    ン
    1.31
    anlı
    1.21
    n
    1.20
    POSITIVE LOGITS
    大
    1.58
     for
    1.34
    原因
    1.32
    手法
    1.23
    人
    1.19
    方法
    1.11
    (
    1.09
    人工智能
    1.07
    是什么
    1.05
    不
    1.05
    Activations Density 0.077%

    No Known Activations