© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199342
    Prev
    Next
    INDEX
    Explanations

    registering listeners or callbacks

    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_27_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
    লিখিত
    0.43
    िलासपुर
    0.42
    แยก
    0.37
    污染
    0.37
    鉉
    0.37
     yoktur
    0.36
     अफे
    0.36
    स्थापित
    0.36
     cerveau
    0.36
     pollute
    0.36
    POSITIVE LOGITS
     Seven
    0.38
     Hundred
    0.37
     المصفوفه
    0.36
    回头
    0.36
     Kathleen
    0.35
    ATOM
    0.35
    藕
    0.35
     pasando
    0.35
     teh
    0.34
     Lender
    0.34
    Activations Density 0.001%

    No Known Activations