© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177417
    Prev
    Next
    INDEX
    Explanations

    city names

    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
    Not in Any Lists

    No Comments

    Negative Logits
    пот
    0.38
     Berlin
    0.37
    StorageSync
    0.37
     puisse
    0.37
    Berlin
    0.36
     ͡
    0.36
    িয়েত
    0.36
    erkraut
    0.35
    Polar
    0.35
     Harman
    0.35
    POSITIVE LOGITS
     simul
    0.41
    陏
    0.40
     Simul
    0.39
     jual
    0.39
    ೂರ್ಣ
    0.38
     மயில
    0.38
     major
    0.38
     sher
    0.38
     MAJOR
    0.38
    SR
    0.37
    Activations Density 0.003%

    No Known Activations