© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 37-GEMMASCOPE-2-TRANSCODER-262K
    4. 136553
    Prev
    Next
    INDEX
    Explanations

    countries and regions

    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_37_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
     légumes
    0.41
     liberated
    0.40
     Teri
    0.39
     Anders
    0.39
     Millet
    0.39
    Teri
    0.38
    ATORS
    0.37
    ặ
    0.37
     EURO
    0.36
     ارو
    0.36
    POSITIVE LOGITS
    ldes
    0.38
     تردد
    0.37
    тный
    0.36
    强的
    0.36
    archiviato
    0.35
    క
    0.35
    강
    0.35
     بقدر
    0.35
    াম
    0.35
     காண்ப
    0.35
    Activations Density 0.007%

    No Known Activations