© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 77678
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    Peq
    0.44
    ぜ
    0.36
     Unite
    0.35
    MenuItemView
    0.35
    গায়
    0.35
    ScrollView
    0.34
     юни
    0.33
     ADMINISTRATION
    0.33
     डॉक्यूमेंट्री
    0.33
     プリント
    0.32
    POSITIVE LOGITS
    同行
    0.38
     বাসায়
    0.36
     হাসপাতাল
    0.36
     oder
    0.35
     Feldman
    0.35
     recibido
    0.35
     藤
    0.34
     receb
    0.34
     ie
    0.34
     nol
    0.34
    Activations Density 0.002%

    No Known Activations