© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63260
    Prev
    Next
    INDEX
    Explanations

    modulo operation: remainder of division

    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_41_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
     عندها
    0.44
     её
    0.37
     Hoskins
    0.37
    öh
    0.36
    ౖ
    0.36
     nü
    0.36
     равна
    0.35
     hosting
    0.34
     ضمن
    0.34
    ެ
    0.34
    POSITIVE LOGITS
     covers
    0.41
     direttamente
    0.39
     Directly
    0.38
     shore
    0.37
     Covers
    0.37
     span
    0.37
     dividir
    0.36
     Milli
    0.36
    ridas
    0.35
     Shores
    0.35
    Activations Density 0.001%

    No Known Activations