© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4802
    Prev
    Next
    INDEX
    Explanations

    in bio

    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
     поддержи
    1.53
    ו
    1.45
     만큼
    1.38
     cil
    1.38
    copter
    1.36
    pooled
    1.34
     subgraph
    1.34
    о
    1.31
     $$\
    1.29
     Villain
    1.27
    POSITIVE LOGITS
    ה
    1.72
    gameOver
    1.50
    a
    1.49
     wiadomo
    1.48
    큼
    1.43
    cgColor
    1.34
    ا
    1.32
    潢
    1.32
    noodles
    1.29
     Пере
    1.29
    Activations Density 0.021%

    No Known Activations