© 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. 212057
    Prev
    Next
    INDEX
    Explanations

    Founding principles and Fathers

    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
     EVAL
    0.44
    த்திற்காக
    0.43
     WndProc
    0.42
    确保
    0.41
    सुन
    0.41
     thúc
    0.41
     Raúl
    0.40
     Reisen
    0.38
    apanicolaou
    0.38
    旛
    0.38
    POSITIVE LOGITS
    לים
    0.48
    riks
    0.47
    ஷ்ட
    0.46
    ृति
    0.46
    Legacy
    0.44
    льнявыя
    0.44
    uj
    0.43
    CS
    0.43
     ook
    0.42
     ame
    0.42
    Activations Density 0.001%

    No Known Activations