© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37941
    Prev
    Next
    INDEX
    Explanations

    Chinese characters and romanizations

    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_11_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
    ت
    0.42
    वारे
    0.42
     downloader
    0.41
    files
    0.41
    Louise
    0.40
     zet
    0.40
    ফ
    0.40
    Aw
    0.39
    кг
    0.39
    ड
    0.39
    POSITIVE LOGITS
     і
    0.45
    粋
    0.42
     classique
    0.40
     сучас
    0.40
    ostante
    0.39
     и
    0.38
     penultimate
    0.38
     και
    0.38
     ו
    0.38
     mercenary
    0.37
    Activations Density 0.011%

    No Known Activations