© 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. 4265
    Prev
    Next
    INDEX
    Explanations

    Paris, Strengths, Windows, news

    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
    ᔭ
    0.39
    产
    0.38
     fastest
    0.37
     quickest
    0.37
     энер
    0.36
     ফেলা
    0.36
     பச
    0.35
    quinoxalin
    0.35
    ধে
    0.35
    Byte
    0.34
    POSITIVE LOGITS
    Paris
    0.40
    隨
    0.40
     Zuf
    0.39
     Novel
    0.38
    قي
    0.38
     Paris
    0.38
    パリ
    0.38
     París
    0.37
    लेस
    0.36
     Yangtze
    0.36
    Activations Density 0.046%

    No Known Activations