© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93234
    Prev
    Next
    INDEX
    Explanations

    Roman numerals

    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_60_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
    1
    1.14
     ١
    0.96
     ૧
    0.88
    １
    0.86
     ۱
    0.84
    ١
    0.80
     ၁
    0.77
    ೧
    0.73
    ᱑
    0.71
     ១
    0.71
    POSITIVE LOGITS
    十八
    0.49
    十七
    0.49
    XVII
    0.45
    十六
    0.45
     Sixteen
    0.45
     Seventeen
    0.44
     sixteen
    0.41
     seventeenth
    0.41
     XVII
    0.41
     XVI
    0.40
    Activations Density 0.034%

    No Known Activations