© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 218674
    Prev
    Next
    INDEX
    Explanations

    North South

    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_47_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    america
    0.43
     Amérique
    0.43
    amerika
    0.42
     امریکا
    0.41
    américa
    0.41
    ╲
    0.41
     America
    0.39
     améric
    0.39
     estadounid
    0.39
    ^{-\
    0.39
    POSITIVE LOGITS
    ten
    0.47
     Anzeige
    0.40
    en
    0.39
     Zeiten
    0.39
     en
    0.39
    те
    0.38
     नाहीत
    0.38
    nian
    0.38
    ेंसिल
    0.36
    ern
    0.35
    Activations Density 0.000%

    No Known Activations