© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130812
    Prev
    Next
    INDEX
    Explanations

    Deutsche

    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_50_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
     הרו
    0.43
    LEA
    0.40
     gyr
    0.40
     Navarro
    0.39
     ଗ
    0.39
     Phen
    0.39
    Recognition
    0.37
    ဠ
    0.37
     المج
    0.37
    পিত
    0.37
    POSITIVE LOGITS
    Deutsche
    1.28
     Deutsche
    1.23
     Deut
    1.20
     Deutsch
    1.20
    Deutsch
    1.11
     deutsch
    1.02
     데
    0.99
    deutsch
    0.98
     Deutschen
    0.97
     deut
    0.96
    Activations Density 0.000%

    No Known Activations