© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148418
    Prev
    Next
    INDEX
    Explanations

    often 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_23_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
     ڕ
    0.47
     extinct
    0.42
    ラック
    0.39
    CharArray
    0.39
    utrients
    0.39
     ಫ
    0.37
     শুদ্ধ
    0.37
     वें
    0.37
    Fmat
    0.37
     تمارين
    0.37
    POSITIVE LOGITS
    Ainsi
    0.51
     inspection
    0.47
     that
    0.45
     Herzen
    0.43
    that
    0.42
    amen
    0.42
     imagery
    0.41
    š
    0.40
     inspecting
    0.40
     bizi
    0.39
    Activations Density 0.002%

    No Known Activations