© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91129
    Prev
    Next
    INDEX
    Explanations

    Greek, Thai, or .NET related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    म
    0.72
    1
    0.68
    2
    0.64
    a
    0.61
    ની
    0.61
    ين
    0.60
    iz
    0.59
    지
    0.58
    ISO
    0.58
    OO
    0.58
    POSITIVE LOGITS
     извър
    0.59
     liten
    0.58
    劶
    0.57
     ойнотуу
    0.55
     endoplasmic
    0.55
     ойно
    0.54
    ">$
    0.54
     acetonitrile
    0.54
     weet
    0.54
     naran
    0.54
    Activations Density 0.000%

    No Known Activations