Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 26-GEMMASCOPE-2-TRANSCODER-262K
    4. 196410
    Prev
    Next
    INDEX
    Explanations

    phase 1

    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_26_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
     Suites
    0.39
     Exec
    0.39
     ص
    0.37
    展开
    0.36
    expose
    0.35
     펼
    0.35
     दू
    0.35
    à
    0.35
     synonym
    0.34
    NZ
    0.34
    POSITIVE LOGITS
     Viitattu
    0.41
     reminders
    0.38
    有名な
    0.38
    複製
    0.38
     vegetables
    0.37
     убе
    0.36
     dummies
    0.36
    研究生
    0.36
    懷
    0.36
    ட்டால்
    0.36
    Activations Density 0.013%

    No Known Activations