© 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. 83132
    Prev
    Next
    INDEX
    Explanations

    Google

    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
     pre
    0.48
    dc
    0.40
     Pre
    0.39
     sund
    0.39
    ipennis
    0.37
    jb
    0.37
    题
    0.37
    кр
    0.36
     lab
    0.36
     dc
    0.36
    POSITIVE LOGITS
    ಹು
    0.43
     होला
    0.41
    போதும்
    0.40
     স্নে
    0.38
    ামা
    0.37
    VIAF
    0.36
     Huo
    0.36
     Successfully
    0.36
    apä
    0.35
     artefact
    0.35
    Activations Density 0.006%

    No Known Activations