© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51658
    Prev
    Next
    INDEX
    Explanations

    e-commerce, e-Procurement, digital stamps, license

    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_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    の間
    0.39
    О
    0.38
    كان
    0.38
    یک
    0.38
    ণ
    0.36
    ת
    0.36
    एक
    0.36
    با
    0.36
    или
    0.35
    社会
    0.35
    POSITIVE LOGITS
    ur
    0.50
     smartwatch
    0.40
     nível
    0.39
     metaverse
    0.38
     tablets
    0.38
     memos
    0.38
     गर्नु
    0.38
    াধিকার
    0.37
    f
    0.37
     microbes
    0.36
    Activations Density 0.018%

    No Known Activations