© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175236
    Prev
    Next
    INDEX
    Explanations

    multilingual fragments

    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_50_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
    pr
    0.44
    ᄇ
    0.44
    부
    0.44
     tarik
    0.43
    пр
    0.42
     Pram
    0.41
    bu
    0.41
     ca
    0.41
    oules
    0.40
    β
    0.40
    POSITIVE LOGITS
     eloquently
    0.44
     Kab
    0.42
    Kab
    0.41
     kab
    0.39
     erfolgreich
    0.37
    kab
    0.37
    rym
    0.37
     eloquent
    0.37
     popularized
    0.37
    ANTH
    0.37
    Activations Density 0.002%

    No Known Activations