© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 65028
    Prev
    Next
    INDEX
    Explanations

    am

    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_51_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
     rij
    0.43
    زاء
    0.42
     tg
    0.41
    ски
    0.40
    erende
    0.39
     چاہی
    0.37
    органи
    0.37
     caric
    0.37
    тоо
    0.36
    조
    0.36
    POSITIVE LOGITS
     Ávila
    0.43
     disrupted
    0.39
     nguyện
    0.39
    انية
    0.38
    一方面
    0.38
     Abit
    0.38
    enie
    0.37
    Lion
    0.37
     franqu
    0.37
    lemish
    0.36
    Activations Density 0.000%

    No Known Activations