© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62629
    Prev
    Next
    INDEX
    Explanations

    liking something / kindly to

    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_11_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
    ش
    0.58
    مل
    0.57
    š
    0.54
    ş
    0.52
    ш
    0.50
     Z
    0.49
    стве
    0.48
     “
    0.48
     JSON
    0.48
    śmy
    0.47
    POSITIVE LOGITS
     นี้
    0.59
     offrir
    0.57
     oxyd
    0.52
    ੯
    0.52
     đãi
    0.51
    ୯
    0.49
     dễ
    0.48
     वीडियोस
    0.48
     есть
    0.48
    ﾍ
    0.47
    Activations Density 0.000%

    No Known Activations