© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54719
    Prev
    Next
    INDEX
    Explanations

    animation and transition

    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_30_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
     парламента
    0.41
     proces
    0.40
     berjalan
    0.40
    峒
    0.39
     বুকে
    0.39
     evaluar
    0.38
     irreg
    0.38
    撹
    0.38
    調理
    0.38
    crawler
    0.38
    POSITIVE LOGITS
     subsidized
    0.48
     slammed
    0.39
     subsidy
    0.39
    费用
    0.37
     cloudy
    0.37
     settled
    0.36
     knife
    0.36
     fast
    0.35
     southeast
    0.35
     hammer
    0.35
    Activations Density 0.011%

    No Known Activations