© 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. 248074
    Prev
    Next
    INDEX
    Explanations

    coins

    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
     shade
    1.41
     Shade
    1.27
     f
    1.22
    shade
    1.16
     colour
    1.11
     colours
    1.03
    색
    1.03
     цвета
    1.01
    色
    1.01
     رنگ
    1.00
    POSITIVE LOGITS
     Cor
    0.42
    ద్ధి
    0.35
     witches
    0.35
     Commod
    0.35
     kome
    0.35
     Coins
    0.35
     cor
    0.34
    Cor
    0.34
    fighter
    0.34
    Coins
    0.33
    Activations Density 0.009%

    No Known Activations