© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134235
    Prev
    Next
    INDEX
    Explanations

    door opening

    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_37_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
     closed
    1.38
     закры
    1.38
     closure
    1.34
     closes
    1.31
     closing
    1.26
     Closed
    1.26
     Closing
    1.24
    闭
    1.22
     closures
    1.20
     Closure
    1.20
    POSITIVE LOGITS
     откры
    1.17
     öpp
    1.16
     opening
    1.13
     відкри
    1.13
    Opening
    1.07
     otev
    1.07
     Opening
    1.06
     открытие
    1.05
     mở
    1.05
     åp
    1.03
    Activations Density 0.005%

    No Known Activations