© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205961
    Prev
    Next
    INDEX
    Explanations

    Spanish verb endings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     σας
    0.66
    ujete
    0.57
     вам
    0.56
     jums
    0.56
     Вам
    0.54
     Вас
    0.54
     您
    0.54
     вас
    0.54
    ของคุณ
    0.53
     Tu
    0.52
    POSITIVE LOGITS
     os
    1.12
     vá
    1.09
    Os
    0.95
     ва
    0.94
     Os
    0.93
     Vá
    0.83
    os
    0.79
     v
    0.78
     OS
    0.76
     w
    0.75
    Activations Density 0.001%

    No Known Activations