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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 2883
    Prev
    Next
    INDEX
    Explanations

    variable assignment

    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
    𝗻
    0.82
    от
    0.69
     nắng
    0.68
    р
    0.68
    жды
    0.68
    CU
    0.68
     stints
    0.66
    𝗮
    0.66
    ну
    0.65
    Thời
    0.64
    POSITIVE LOGITS
    र्देश
    0.72
    stituted
    0.70
     কিন্তু
    0.68
     confounding
    0.66
    ꧁
    0.65
    ੋ
    0.63
    서는
    0.62
     când
    0.62
     traité
    0.62
    sburg
    0.60
    Activations Density 0.002%

    No Known Activations