© 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. 228734
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis

    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
    ্যে
    0.37
     Videos
    0.37
    㖷
    0.36
     वीडियोस
    0.36
    ㅑ
    0.36
    oplanes
    0.36
     mun
    0.35
    ํ
    0.35
    opolys
    0.35
     했다
    0.35
    POSITIVE LOGITS
    Sharon
    0.37
    Sus
    0.35
    Ruth
    0.35
     Susana
    0.35
     Bridget
    0.34
    स्टेप
    0.34
    সেল
    0.34
    aust
    0.33
    SUS
    0.33
     précise
    0.33
    Activations Density 0.007%

    No Known Activations