© 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. 170392
    Prev
    Next
    INDEX
    Explanations

    best results or smoother experience

    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
    зон
    0.23
    தி
    0.23
    可愛い
    0.23
    extreme
    0.22
     meso
    0.22
     coalgebra
    0.22
     außergewöhn
    0.22
    朋友
    0.21
    abbanti
    0.21
    𝚣
    0.21
    POSITIVE LOGITS
     Uttar
    0.24
     Retrieved
    0.24
     It
    0.23
    ंगल
    0.23
    Kiev
    0.22
     raid
    0.22
     Norton
    0.21
    dB
    0.21
    ảm
    0.21
    Norton
    0.21
    Activations Density 0.008%

    No Known Activations