© 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. 8638
    Prev
    Next
    INDEX
    Explanations

    Japanese names and words

    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
    क
    3.28
     preventable
    2.74
     menget
    2.62
    娆
    2.62
     parentheses
    2.60
    힙
    2.56
    en
    2.53
    빚
    2.52
    突出
    2.51
    begin
    2.51
    POSITIVE LOGITS
    ść
    2.29
     antal
    2.25
    ති
    2.25
    ോട്ട്
    2.19
    ാൻഡ്
    2.16
     ponerse
    2.14
    zeug
    2.10
     anecd
    2.08
    toolStrip
    2.04
    ність
    2.03
    Activations Density 0.010%

    No Known Activations