© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135491
    Prev
    Next
    INDEX
    Explanations

    base64 encoded strings

    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_6_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    aneous
    1.05
    ENT
    1.01
    ：
    0.97
    ER
    0.95
    ☛
    0.95
     Tạo
    0.94
    8
    0.93
     করিতেছি
    0.93
    =\
    0.92
     করিয়াছিলেন
    0.92
    POSITIVE LOGITS
    ת
    1.61
    t
    1.52
    y
    1.40
    ت
    1.39
    ق
    1.38
    ش
    1.23
     in
    1.20
    ம்
    1.17
    تك
    1.15
    ج
    1.15
    Activations Density 0.002%

    No Known Activations