© 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. 211966
    Prev
    Next
    INDEX
    Explanations

    proposes development of a project

    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
     जीतकर
    0.18
     threefold
    0.17
    を結
    0.17
     करेगा
    0.17
    䣷
    0.17
    Animation
    0.16
    রব
    0.16
    Seqlist
    0.16
    lamualaikum
    0.16
    दस
    0.16
    POSITIVE LOGITS
    Ys
    0.18
     PC
    0.17
    ře
    0.17
    не
    0.16
    similar
    0.16
     kV
    0.16
     antir
    0.15
    ))}{
    0.15
    ))$,
    0.15
     Paco
    0.15
    Activations Density 0.001%

    No Known Activations