© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 195755
    Prev
    Next
    INDEX
    Explanations

    glucose and sugar

    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_26_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
    蛲
    0.46
     клини
    0.43
    㥉
    0.43
    ଗ
    0.42
    र्देश
    0.42
     सूत्रकृ
    0.42
    蝗
    0.42
    㔯
    0.42
     লক্ষণ
    0.42
    ব
    0.41
    POSITIVE LOGITS
    -
    0.50
     \
    0.50
     რომ
    0.46
     \\
    0.43
     koji
    0.42
     didn
    0.42
     $
    0.40
    Oj
    0.40
     jego
    0.40
    ype
    0.40
    Activations Density 0.001%

    No Known Activations