© 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. 66116
    Prev
    Next
    INDEX
    Explanations

    Hong Kong

    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
     along
    0.43
     китай
    0.39
    沿
    0.38
    ᅵ
    0.38
    China
    0.37
    Chinese
    0.37
     theo
    0.36
    Along
    0.36
     zh
    0.35
     chines
    0.35
    POSITIVE LOGITS
     Po
    0.38
     ท
    0.38
    house
    0.37
     वेरी
    0.37
    ંદા
    0.36
     Long
    0.36
     newdata
    0.36
     पीओ
    0.36
    ทาน
    0.35
    സ്ട
    0.35
    Activations Density 0.000%

    No Known Activations