© 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-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3572
    Prev
    Next
    INDEX
    Explanations

    tikz code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    ीय
    0.93
    enst
    0.92
    erà
    0.90
    ladesh
    0.88
    ствием
    0.86
    ▌
    0.85
    eské
    0.85
    kiyor
    0.84
    ارع
    0.83
    ﻪ
    0.83
    POSITIVE LOGITS
    서
    0.91
    ச
    0.90
    c
    0.84
    岖
    0.82
    د
    0.80
     regard
    0.77
    خ
    0.76
    تی
    0.75
     subst
    0.74
    ra
    0.73
    Activations Density 0.003%

    No Known Activations