© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30887
    Prev
    Next
    INDEX
    Explanations

    `:` and `.` in code

    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_31_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
     Tax
    0.36
     {
    0.35
     Finite
    0.34
     i
    0.33
     May
    0.33
     Text
    0.33
    //
    0.33
     Pat
    0.33
    irea
    0.33
     Patagonia
    0.32
    POSITIVE LOGITS
    淉
    0.36
    رك
    0.35
    chun
    0.34
    рован
    0.34
     secondaires
    0.34
    Leng
    0.33
    AssetName
    0.33
    puce
    0.33
    촬
    0.33
    ্ধ
    0.33
    Activations Density 0.008%

    No Known Activations