© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86812
    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_23_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
     because
    0.44
    =/
    0.44
     leo
    0.41
     sebag
    0.40
    bigger
    0.40
     dices
    0.40
     preview
    0.39
     inspect
    0.39
    \;
    0.38
     sebagai
    0.38
    POSITIVE LOGITS
     রাকাত
    0.45
     поддержи
    0.44
     Акы
    0.44
     ਤੁਹਾ
    0.43
     উদ্ভিদ
    0.42
     جمعه
    0.42
     помещения
    0.42
     ተመሳሳይ
    0.42
    薬品
    0.41
    靭
    0.41
    Activations Density 0.000%

    No Known Activations