© 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. 212897
    Prev
    Next
    INDEX
    Explanations

    travel

    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
    Avro
    0.42
    Ku
    0.42
    Vu
    0.40
    Wu
    0.40
    カー
    0.40
    Kur
    0.40
    Brussels
    0.39
    A
    0.39
    KU
    0.39
     A
    0.39
    POSITIVE LOGITS
     حلو
    0.45
     диви
    0.44
    ਤੇ
    0.40
    టే
    0.38
     laranja
    0.38
     Farrar
    0.38
    ('/\
    0.38
     انف
    0.38
     मध्य
    0.37
     horseshoe
    0.37
    Activations Density 0.000%

    No Known Activations