© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 83303
    Prev
    Next
    INDEX
    Explanations

    Gl

    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_53_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
     LON
    0.41
    ベット
    0.37
    jdbcType
    0.36
     বেতার
    0.36
    寶
    0.36
     Бет
    0.35
    ება
    0.35
     랜
    0.35
    arek
    0.34
    enswert
    0.34
    POSITIVE LOGITS
    циях
    0.48
     epidemi
    0.46
     coronavirus
    0.41
     mod
    0.41
    捱
    0.41
     duda
    0.40
    ruga
    0.40
     코로나
    0.40
     epid
    0.40
    మారు
    0.39
    Activations Density 0.001%

    No Known Activations