© 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-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 66462
    Prev
    Next
    INDEX
    Explanations

    decompose

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     بوت
    0.46
     Canterbury
    0.39
     Templ
    0.39
    River
    0.38
     shepherds
    0.38
    fieldContext
    0.38
    템
    0.37
    봇
    0.37
     Cavalry
    0.37
    pseud
    0.37
    POSITIVE LOGITS
     decompose
    0.44
     decomposed
    0.43
    分解
    0.42
    LaunchAction
    0.39
    Դ
    0.39
    ⦕
    0.39
     decomposes
    0.38
    myForm
    0.38
     decomposing
    0.37
    decompose
    0.37
    Activations Density 0.015%

    No Known Activations