© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5362
    Prev
    Next
    INDEX
    Explanations

    bypass local admin

    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_3_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
    ي
    3.58
    م
    3.42
    y
    2.83
    j
    2.66
    واره
    2.66
    i
    2.60
    ि
    2.58
    ки
    2.56
    ة
    2.56
    is
    2.50
    POSITIVE LOGITS
     denen
    2.31
     veille
    2.22
    ς
    2.22
    ы
    2.20
     aden
    2.16
     aliqu
    2.12
    즐
    2.08
     postulate
    2.08
     jamais
    2.07
    是要
    1.98
    Activations Density 0.001%

    No Known Activations