© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170265
    Prev
    Next
    INDEX
    Explanations

    Buddhism

    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_20_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
     प्रकारे
    0.41
    ,"@
    0.34
    专业的
    0.34
     Gaga
    0.34
    '&
    0.34
     есте
    0.33
    `,
    0.33
     برخ
    0.33
    ੍ਰ
    0.33
     बख
    0.33
    POSITIVE LOGITS
     admon
    0.38
    memset
    0.37
     Founding
    0.35
    ונות
    0.34
    簟
    0.33
     wcześniej
    0.33
    ណ្ឌ
    0.33
     نیٹ
    0.32
     malware
    0.32
     pile
    0.32
    Activations Density 0.002%

    No Known Activations