© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 247993
    Prev
    Next
    INDEX
    Explanations

    knock

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     wall
    1.41
    wall
    1.21
    Wall
    1.09
     Wall
    1.04
    WALL
    1.02
    壁
    1.02
     WALL
    1.01
     벽
    0.98
    墙
    0.90
     duvar
    0.89
    POSITIVE LOGITS
     knock
    1.63
     knocking
    1.52
     knocked
    1.50
     Knock
    1.42
     knocks
    1.40
    knock
    1.26
     knockdown
    1.18
     knockout
    1.14
    Kn
    0.88
     Knox
    0.67
    Activations Density 0.020%

    No Known Activations