© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219727
    Prev
    Next
    INDEX
    Explanations

    Houston

    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_47_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
     cerv
    0.39
    ギュ
    0.38
    র্জেন্ট
    0.38
     loaf
    0.37
    ŗ
    0.37
     अदा
    0.37
    igungen
    0.37
     yù
    0.36
    тур
    0.36
    TRY
    0.36
    POSITIVE LOGITS
    Valley
    0.45
     Valley
    0.42
    valley
    0.40
     toată
    0.39
     lightbox
    0.38
     VALLEY
    0.38
    Alt
    0.37
     Altos
    0.37
    ätta
    0.37
    ᑯ
    0.37
    Activations Density 0.000%

    No Known Activations