© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 159145
    Prev
    Next
    INDEX
    Explanations

    linguistic origins

    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
     호
    0.54
    HO
    0.47
    호
    0.47
    호를
    0.46
     Ho
    0.46
     хо
    0.43
     Хо
    0.42
    хо
    0.42
     Hon
    0.42
    厚
    0.42
    POSITIVE LOGITS
     род
    0.46
    shank
    0.42
     Ruler
    0.41
    ব্র
    0.41
    Multip
    0.41
    브
    0.41
    Br
    0.39
     Multip
    0.39
     Brahman
    0.39
     brat
    0.39
    Activations Density 0.020%

    No Known Activations