© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130717
    Prev
    Next
    INDEX
    Explanations

    contrast or qualification

    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_25_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
    潾
    0.37
     lavoratori
    0.36
    ಳು
    0.34
     разум
    0.34
    𝚗
    0.34
    锼
    0.33
    (!)
    0.32
    hydrocèle
    0.32
    িনী
    0.32
    ரசுக்
    0.32
    POSITIVE LOGITS
    ൨
    0.37
     other
    0.35
    Missing
    0.34
    ？
    0.33
     dampers
    0.33
    其他
    0.33
    ?/
    0.32
    西班牙
    0.32
     egyéb
    0.32
     Ä
    0.32
    Activations Density 0.014%

    No Known Activations