© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 201269
    Prev
    Next
    INDEX
    Explanations

    places names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     scribble
    0.42
    Minimize
    0.41
     ಗು
    0.41
    বাংলা
    0.39
     Minimize
    0.38
    ࣪
    0.38
    ませんが
    0.37
     ବ
    0.37
    iria
    0.37
    dater
    0.36
    POSITIVE LOGITS
     Cerc
    0.45
    Camp
    0.44
     Abou
    0.43
     Shen
    0.42
     మహా
    0.42
    Shore
    0.41
     নর
    0.41
    棈
    0.39
     Camp
    0.39
    Nor
    0.39
    Activations Density 0.005%

    No Known Activations