© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 212553
    Prev
    Next
    INDEX
    Explanations

    switch or button

    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_19_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
     unfortunate
    0.47
    今回
    0.46
     intensively
    0.45
     ინ
    0.44
    验
    0.44
     ரசிக
    0.44
     UK
    0.44
     yaşam
    0.44
    ve
    0.44
     verlei
    0.44
    POSITIVE LOGITS
    Fols
    0.46
     кнопки
    0.45
    itipi
    0.44
     سپر
    0.44
    냅
    0.43
    的大小
    0.43
    ajouter
    0.43
    mana
    0.43
    زر
    0.42
    이트
    0.42
    Activations Density 0.001%

    No Known Activations