© 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. 88942
    Prev
    Next
    INDEX
    Explanations

    commander. cakes. cake. codes. keycode. keysym. barnes. conversion. services. establishments. cocktails. пени. fillings. proposals. resolutions. constituencies. expectations. simulations. compositions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    記錄
    0.53
    อน
    0.49
    tedir
    0.48
    ный
    0.46
    有一個
    0.46
    ë
    0.46
    ренный
    0.45
     Ві
    0.45
     nią
    0.45
    璈
    0.45
    POSITIVE LOGITS
     expectations
    0.62
     compositions
    0.54
     establishments
    0.49
     simulations
    0.47
     cocktails
    0.47
    пени
    0.47
     fillings
    0.47
     proposals
    0.46
     resolutions
    0.46
     constituencies
    0.46
    Activations Density 0.000%

    No Known Activations