© 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
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12089
    Prev
    Next
    INDEX
    Explanations

    a or an or una or un

    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_13_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
     अधिकारियों
    0.23
     Новосибир
    0.22
     adolescents
    0.21
     उपकरण
    0.21
    ния
    0.20
    𝒞
    0.20
    Ꮸ
    0.20
     स्टूडेंट्स
    0.20
     музыкан
    0.19
     студентов
    0.19
    POSITIVE LOGITS
    p
    0.23
     \
    0.22
    কু
    0.22
    os
    0.21
     tinge
    0.21
    ouette
    0.21
    >
    0.20
     it
    0.20
    érêt
    0.20
    od
    0.20
    Activations Density 0.054%

    No Known Activations