© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 210506
    Prev
    Next
    INDEX
    Explanations

    rope

    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_10_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
    ;
    0.76
    ки
    0.75
     lhe
    0.72
     l
    0.70
     Mariah
    0.65
     lanz
    0.64
    सि
    0.63
    うまく
    0.63
    க
    0.63
    n
    0.63
    POSITIVE LOGITS
    has
    0.74
    aft
    0.68
    NewLine
    0.66
    had
    0.65
    ਾਲ
    0.65
    NPC
    0.65
    StartsWith
    0.64
    OS
    0.64
    ToolTip
    0.64
    LSTM
    0.63
    Activations Density 0.000%

    No Known Activations