© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14162
    Prev
    Next
    INDEX
    Explanations

    phonetic spelling and pronunciation guides

    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
    ER
    0.64
    ING
    0.54
    ద
    0.54
    SelectSingle
    0.50
     الأطفال
    0.50
    ون
    0.48
    нду
    0.48
    ة
    0.48
    шат
    0.48
     Accounts
    0.48
    POSITIVE LOGITS
     gyors
    0.52
     comida
    0.49
     വ്യ
    0.49
     dirigido
    0.47
     quelles
    0.47
     brazo
    0.46
     zákaz
    0.46
     கி
    0.46
     springing
    0.46
     bhith
    0.46
    Activations Density 0.038%

    No Known Activations