© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257312
    Prev
    Next
    INDEX
    Explanations

    small number, amount, slice, percentage

    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_22_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
    ダンス
    0.40
    Liquid
    0.39
    ᅮ
    0.39
    lvmama
    0.38
    Ọ
    0.38
    GLAND
    0.38
    ᅩ
    0.38
    +][
    0.38
    бити
    0.38
    ean
    0.37
    POSITIVE LOGITS
     streetlight
    0.46
     ingred
    0.45
     exuber
    0.43
    মন্ত্রীর
    0.42
     dihedral
    0.42
     rasgos
    0.42
     photovolta
    0.41
    ifiably
    0.41
     cannab
    0.41
     kW
    0.40
    Activations Density 0.003%

    No Known Activations