© 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. 167936
    Prev
    Next
    INDEX
    Explanations

    रही, जाएगा, सकते, चुकी, गई

    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
    ंपरिक
    0.39
    strategic
    0.37
     kiedy
    0.36
     стратеги
    0.35
     σημαν
    0.35
     回
    0.35
     যেখানে
    0.35
     전략
    0.34
     مهم
    0.34
    战略
    0.34
    POSITIVE LOGITS
    殆
    0.39
     reed
    0.38
    cuenta
    0.37
     Blaine
    0.36
     Konto
    0.36
     regained
    0.35
     gaping
    0.35
     mined
    0.35
     vergangenen
    0.35
     Cuenta
    0.35
    Activations Density 0.000%

    No Known Activations