© 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
    2. Gemma-3-27B-IT
    3. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 198611
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    SPC
    0.48
     willingness
    0.41
     완
    0.41
     SPC
    0.41
     시간이
    0.40
     SPS
    0.40
     невозможно
    0.40
     مدى
    0.40
    ว้าง
    0.39
    ਦਾ
    0.38
    POSITIVE LOGITS
    ̣i
    0.42
     Daughter
    0.40
    Met
    0.40
     Fungsi
    0.40
    甸
    0.39
     Cib
    0.38
     ء
    0.37
     प्
    0.36
     Hasil
    0.36
    檢查
    0.36
    Activations Density 0.015%

    No Known Activations