© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8022
    Prev
    Next
    INDEX
    Explanations

    Cinco de Mayo, coat of arms, Champ de Mars

    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
    mselves
    0.90
    _{+}+
    0.87
    el
    0.86
    不可以
    0.79
    NSString
    0.78
    im
    0.77
    ही
    0.75
    ㄨ
    0.74
     helplessness
    0.73
     `${
    0.73
    POSITIVE LOGITS
     daraus
    0.86
    g
    0.77
    issantes
    0.75
    ע
    0.73
     verts
    0.72
    да
    0.71
     trein
    0.69
     propre
    0.68
    لت
    0.68
    ∂
    0.68
    Activations Density 0.002%

    No Known Activations