© 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. 261356
    Prev
    Next
    INDEX
    Explanations

    庄严/上火/上课/达成

    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
    al
    2.05
    e
    2.00
    s
    2.00
    t
    1.87
    é
    1.72
    d
    1.63
     as
    1.55
    y
    1.55
    (
    1.44
     a
    1.43
    POSITIVE LOGITS
    ก็
    1.00
    ین
    1.00
     הראש
    0.96
    рачи
    0.95
    िक
    0.94
    มัน
    0.91
    티
    0.91
    ิน
    0.89
    خدام
    0.89
    ак
    0.89
    Activations Density 0.000%

    No Known Activations