© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113399
    Prev
    Next
    INDEX
    Explanations

    cramming / proclamation

    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_2_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
    ر
    1.54
    ς
    1.38
    ти
    1.19
    да
    1.17
    r
    1.16
    تي
    1.14
    ม
    1.14
    т
    1.12
    ер
    1.09
     fertil
    1.09
    POSITIVE LOGITS
     it
    1.70
     a
    1.27
     to
    1.22
    of
    1.17
    的海
    1.17
    od
    1.14
    的对象
    1.13
     It
    1.04
    的技术
    1.03
    ue
    1.01
    Activations Density 0.001%

    No Known Activations