© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192564
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_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
    ە
    0.52
    erevan
    0.51
     atoms
    0.50
     alak
    0.48
     Afghanistan
    0.48
     herbs
    0.48
     recognizing
    0.48
    ്‍
    0.47
    มะ
    0.47
     ವಿದ
    0.47
    POSITIVE LOGITS
    >
    0.52
     dampen
    0.51
    基于
    0.48
     кабинет
    0.47
     পরেই
    0.47
     гром
    0.46
    )
    0.46
    Kill
    0.44
    代谢
    0.44
    .
    0.44
    Activations Density 0.000%

    No Known Activations