© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164887
    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_31_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
     tâ
    0.40
    枓
    0.39
     Vedi
    0.39
    ysk
    0.38
    숴
    0.37
    Ⲡ
    0.37
    瑁
    0.37
    Denovo
    0.37
    ïd
    0.37
     Beds
    0.37
    POSITIVE LOGITS
    味料
    0.41
     الخط
    0.39
    ًا
    0.36
    佈
    0.36
     challenger
    0.36
    0.36
    unin
    0.36
    正常的
    0.35
     outwardly
    0.35
     respiration
    0.35
    Activations Density 0.000%

    No Known Activations