© 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. 198180
    Prev
    Next
    INDEX
    Explanations

    gold

    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
     treasure
    1.64
    宝
    1.55
     Treasure
    1.52
     treasures
    1.45
    treasure
    1.45
     Treasures
    1.35
    Treas
    1.34
    寶
    1.32
     Treasury
    1.26
     treas
    1.24
    POSITIVE LOGITS
     Strauss
    0.41
    LookAndFeelInfo
    0.40
     cyclohexane
    0.39
     écoul
    0.39
    ຟ
    0.38
     Strickland
    0.38
    iklet
    0.37
    lective
    0.37
    طان
    0.37
    พลิ
    0.37
    Activations Density 0.001%

    No Known Activations