© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 19211
    Prev
    Next
    INDEX
    Explanations

    geometric shapes and spacing

    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
    Negative Logits
    ARP
    0.45
     monolithic
    0.44
    雍
    0.41
     Mahmood
    0.40
    includegraphics
    0.39
    ี่ยม
    0.38
     condensers
    0.37
     Stereo
    0.37
    ϑ
    0.36
     estere
    0.36
    POSITIVE LOGITS
     spacing
    1.43
    spacing
    1.32
     spacings
    1.27
    Spacing
    1.26
     spaced
    1.03
    spaced
    0.92
    spac
    0.80
     spacer
    0.77
     lattice
    0.74
    Spaces
    0.73
    Activations Density 0.054%

    No Known Activations