© 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. 91691
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    1
    0.50
    ductor
    0.50
     cursorPos
    0.50
     가장
    0.47
    ﺫ
    0.46
     为
    0.45
    为
    0.45
     ምክንያት
    0.44
     दिन
    0.44
     為
    0.43
    POSITIVE LOGITS
    л
    0.51
    ：（
    0.46
     atuação
    0.46
     ιστο
    0.44
     equities
    0.43
     Yeşil
    0.43
    êts
    0.43
    otika
    0.43
    ién
    0.42
     Nghi
    0.42
    Activations Density 0.000%

    No Known Activations