© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229281
    Prev
    Next
    INDEX
    Explanations

    "prepare yourself mortal"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     overview
    0.43
    時代
    0.43
     era
    0.42
    坟
    0.41
     Authority
    0.40
     Overview
    0.39
    Authority
    0.38
    omen
    0.38
     authority
    0.38
     laps
    0.37
    POSITIVE LOGITS
    FEED
    0.40
    caret
    0.38
     hijas
    0.35
     المحاضره
    0.35
     শুনেছি
    0.35
    ্জ
    0.35
    ZU
    0.34
    Ricky
    0.34
    棟
    0.33
    سان
    0.33
    Activations Density 0.001%

    No Known Activations