© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54658
    Prev
    Next
    INDEX
    Explanations

    followed by descriptive complement

    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_30_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
    MEA
    0.29
    JAN
    0.28
    ("/")
    0.28
     debes
    0.27
    ～
    0.27
     explicando
    0.27
    一流
    0.26
    ISSU
    0.26
    چ
    0.26
    中使用
    0.26
    POSITIVE LOGITS
     також
    0.36
     also
    0.35
     таксама
    0.33
     tiež
    0.30
     QLabel
    0.29
     vyp
    0.29
     hardly
    0.29
     ebenfalls
    0.28
    qtd
    0.28
     slipped
    0.27
    Activations Density 0.009%

    No Known Activations