© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8801
    Prev
    Next
    INDEX
    Explanations

    Greek yogurt

    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_13_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
     यूक्रेन
    0.50
    Otp
    0.50
    Ukraine
    0.47
     Exel
    0.46
     desple
    0.45
     =",
    0.45
    тинен
    0.45
    änen
    0.44
    Volatility
    0.44
    𖥔
    0.44
    POSITIVE LOGITS
    ܕ
    0.57
     Lake
    0.53
    K
    0.53
     soon
    0.51
    merge
    0.51
     within
    0.50
    ende
    0.50
     karm
    0.50
     model
    0.50
    üp
    0.49
    Activations Density 0.002%

    No Known Activations