© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 212113
    Prev
    Next
    INDEX
    Explanations

    Wikipedia

    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_20_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
     zuverläss
    0.49
    버스
    0.47
    挕
    0.46
     温度
    0.45
     دیوار
    0.45
     తయారు
    0.45
     yattha
    0.45
     وړاندوینې
    0.44
     তাপমাত্রা
    0.44
    fireFlower
    0.44
    POSITIVE LOGITS
     +
    0.51
    string
    0.45
     rent
    0.43
    ine
    0.43
    ido
    0.41
    s
    0.41
    +
    0.41
    ин
    0.41
    ス
    0.41
    pre
    0.40
    Activations Density 0.002%

    No Known Activations