© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37201
    Prev
    Next
    INDEX
    Explanations

    their what

    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_11_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
    ెస్
    0.49
    nade
    0.48
     CSO
    0.43
    ни
    0.42
     Vé
    0.42
    ﺴ
    0.41
    klı
    0.41
    ழ்ச்ச
    0.41
    ”!
    0.41
     deviate
    0.40
    POSITIVE LOGITS
    ا
    0.54
    ید
    0.52
    ण्यासाठी
    0.50
    Ο
    0.49
    的
    0.48
     bastante
    0.48
    un
    0.47
    ap
    0.47
     vuonna
    0.47
    ם
    0.47
    Activations Density 0.053%

    No Known Activations