© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13711
    Prev
    Next
    INDEX
    Explanations

    peace be upon him

    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_15_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
     Bab
    0.52
    ătă
    0.52
     parlare
    0.50
    ס
    0.50
    ﺎ
    0.49
     Tig
    0.48
    ادل
    0.48
     Hades
    0.48
     Hotel
    0.47
     Ag
    0.47
    POSITIVE LOGITS
    蓊
    0.56
    Questo
    0.53
     ആദ്യ
    0.52
     नेतृत्व
    0.50
     sarees
    0.48
     北海道
    0.48
     totality
    0.47
     തയ്യാ
    0.47
    ব্রিটিশ
    0.47
     करेंगे
    0.46
    Activations Density 0.001%

    No Known Activations