© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54848
    Prev
    Next
    INDEX
    Explanations

    surname parts

    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_30_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
     तनु
    0.39
    溲
    0.37
    clientsdetails
    0.37
     สืบค้น
    0.37
     افس
    0.36
    เขา
    0.35
     проверки
    0.34
    http
    0.34
    ⓤ
    0.34
    শ্
    0.33
    POSITIVE LOGITS
    igram
    0.40
     Verhältnis
    0.40
     gram
    0.36
    衙
    0.36
    libc
    0.35
    setRoot
    0.35
     Executive
    0.34
    বিধা
    0.34
    ter
    0.34
     Completely
    0.34
    Activations Density 0.000%

    No Known Activations