© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16507
    Prev
    Next
    INDEX
    Explanations

    name="input attribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     يوليو
    0.38
    ຕ່
    0.37
    çuk
    0.36
     setCart
    0.35
     Cfx
    0.35
    拖
    0.35
    طلا
    0.34
     cartas
    0.34
    ฺ
    0.34
    チル
    0.34
    POSITIVE LOGITS
    committed
    0.39
     crash
    0.38
     Sph
    0.36
     Committed
    0.36
    কেশন
    0.36
     方法
    0.35
     Shut
    0.35
    方法
    0.35
     programm
    0.35
    Exam
    0.35
    Activations Density 0.001%

    No Known Activations