© 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. 257266
    Prev
    Next
    INDEX
    Explanations

    width declaration or assignment

    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
    我们的
    0.42
     наши
    0.41
    斯拉
    0.40
     ఒక్క
    0.39
    ouses
    0.38
     nuestras
    0.38
    স্টি
    0.38
    釷
    0.38
    那些
    0.38
     ہمارے
    0.38
    POSITIVE LOGITS
     zar
    0.42
    confirmed
    0.41
     coppia
    0.39
     repetir
    0.39
     täglich
    0.39
    ต่อเนื่อง
    0.39
     zi
    0.38
    ペア
    0.38
     विका
    0.38
     concentração
    0.37
    Activations Density 0.004%

    No Known Activations