© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133651
    Prev
    Next
    INDEX
    Explanations

    ying

    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_1_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
    ت
    1.28
    ри
    1.24
    দের
    1.23
    J
    1.11
    ل
    1.09
    ן
    1.05
    ת
    1.03
    تس
    1.02
    鸪
    1.02
    ク
    0.98
    POSITIVE LOGITS
     nær
    1.01
     acontece
    0.99
     име
    0.97
     basa
    0.93
    0
    0.91
     deti
    0.90
    ص
    0.90
    h
    0.89
    িয়া
    0.88
     guzt
    0.87
    Activations Density 0.001%

    No Known Activations