© 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. 30748
    Prev
    Next
    INDEX
    Explanations

    European cities

    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
    Store
    0.41
     starring
    0.40
     St
    0.39
     elic
    0.39
     zero
    0.38
    நல்ல
    0.37
     Store
    0.36
    St
    0.36
     staging
    0.36
    零
    0.36
    POSITIVE LOGITS
    되지
    0.42
    錡
    0.42
    werpen
    0.40
     jaren
    0.40
     نر
    0.40
    နှုန်း
    0.38
    REND
    0.38
     kiezen
    0.38
     Artik
    0.38
    かの
    0.38
    Activations Density 0.000%

    No Known Activations