© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33149
    Prev
    Next
    INDEX
    Explanations

    rip tear puncture hole perforation

    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_40_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
    multiSelectList
    0.41
     وع
    0.36
     Regal
    0.36
    cheat
    0.36
     ಕೆ
    0.35
    =[],
    0.34
     reactivation
    0.34
     justices
    0.34
    сцю
    0.34
    肤
    0.34
    POSITIVE LOGITS
     holes
    1.91
     hole
    1.89
     Holes
    1.67
     Hole
    1.64
    holes
    1.48
    hole
    1.45
    穴
    1.41
     отверсти
    1.19
     aguj
    1.06
     छेद
    1.04
    Activations Density 0.055%

    No Known Activations