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. 196575
    Prev
    Next
    INDEX
    Explanations

    gemma

    np_acts-logits-general · gemini-2.5-flash-lite

    the start of an assistant/model reply (the token marking the beginning of the model's response).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
    なさ
    0.42
     ดวง
    0.40
     overuse
    0.39
    ्राष्ट्रीय
    0.37
     było
    0.37
    čių
    0.36
    ไทย
    0.36
     dotyczące
    0.36
     seemingly
    0.35
     วิ
    0.35
    POSITIVE LOGITS
     either
    0.42
     fleshy
    0.40
     coars
    0.39
     glutathione
    0.38
     authenticate
    0.38
     clothe
    0.38
    Ji
    0.37
    要么
    0.37
     instar
    0.36
    괄
    0.36
    Activations Density 0.013%

    No Known Activations