© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96878
    Prev
    Next
    INDEX
    Explanations

    checkmate

    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_14_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
    I
    0.62
    IEEE
    0.59
     IEEE
    0.57
     Hitch
    0.55
    T
    0.54
     footer
    0.53
    if
    0.51
     ACM
    0.51
    layout
    0.49
    页面
    0.48
    POSITIVE LOGITS
    鵠
    0.55
     ciertos
    0.55
     банк
    0.54
    )^{-\
    0.52
     divino
    0.52
     insolvent
    0.52
     niž
    0.52
     ruj
    0.51
    liono
    0.50
     бу
    0.50
    Activations Density 0.001%

    No Known Activations