© 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. 229171
    Prev
    Next
    INDEX
    Explanations

    say "sk"

    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
    WindowEvent
    0.44
    নিং
    0.42
    IO
    0.41
    蘊
    0.40
    蕴
    0.40
    ÍN
    0.39
    ობის
    0.38
    І
    0.38
    َق
    0.37
    IQUE
    0.37
    POSITIVE LOGITS
     Sk
    0.72
    Sk
    0.59
     sk
    0.57
     स्की
    0.52
    sk
    0.46
     স্ক
    0.44
    Sku
    0.43
    sku
    0.41
     ск
    0.40
     स्कि
    0.40
    Activations Density 0.001%

    No Known Activations