© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53515
    Prev
    Next
    INDEX
    Explanations

    London areas

    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_55_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
     കുറ
    0.47
     Utilities
    0.46
     Encoding
    0.45
     Cream
    0.44
     Town
    0.42
     encoding
    0.42
    맨
    0.42
    Utilities
    0.41
    娛
    0.41
     Enforcement
    0.41
    POSITIVE LOGITS
    ائح
    0.42
    ປະກອບ
    0.39
    ungy
    0.37
    stringify
    0.37
    inete
    0.36
    ៣
    0.36
    yll
    0.35
    文件中
    0.35
     lightbox
    0.35
    々の
    0.34
    Activations Density 0.000%

    No Known Activations