© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48216
    Prev
    Next
    INDEX
    Explanations

    comparison phrase "X than Y"

    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_31_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
    ̓
    0.42
    Contributors
    0.37
     rightly
    0.37
    Mercedes
    0.37
    Pes
    0.37
     mest
    0.37
    harusnya
    0.37
     rightfully
    0.36
    Cent
    0.35
    Cir
    0.35
    POSITIVE LOGITS
     งวด
    0.39
     konnten
    0.38
     प्रत्यक्ष
    0.37
     desconocido
    0.36
    睁
    0.36
     equipado
    0.36
     يتح
    0.36
    收聽
    0.36
     পিছনে
    0.35
     पासून
    0.35
    Activations Density 0.005%

    No Known Activations