© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81662
    Prev
    Next
    INDEX
    Explanations

    太郎,人类,процесс

    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_0_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
    :
    2.08
    u
    1.82
    д
    1.80
    ↵
    1.74
    ر
    1.74
    6
    1.72
    드
    1.62
    ล
    1.59
    >
    1.58
    ള
    1.52
    POSITIVE LOGITS
     in
    1.39
    s
    1.25
     I
    1.23
     밝혔
    1.19
     дости
    1.16
    sj
    1.15
    dale
    1.12
     BEEN
    1.12
     поги
    1.12
     сообщи
    1.09
    Activations Density 0.000%

    No Known Activations