© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 80498
    Prev
    Next
    INDEX
    Explanations

    foreign language text fragments

    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_29_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
     Encyclop
    0.39
    を使
    0.38
     Gust
    0.36
    驩
    0.36
    郧
    0.36
    gust
    0.35
    ቱን
    0.34
     Runner
    0.33
     corset
    0.33
    許
    0.33
    POSITIVE LOGITS
     நிறை
    0.42
     lundi
    0.39
     warahmatullahi
    0.39
     tratar
    0.39
     संवेदनशील
    0.39
    asyarakat
    0.38
     fortnight
    0.37
    feitura
    0.37
     رفع
    0.37
     lire
    0.37
    Activations Density 0.001%

    No Known Activations