© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33208
    Prev
    Next
    INDEX
    Explanations

    Continiue the Story

    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_3_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
     on
    1.04
     to
    0.89
     Cong
    0.83
     cong
    0.83
     kong
    0.81
    Cong
    0.80
     Kong
    0.80
    es
    0.80
    ü
    0.79
     congr
    0.76
    POSITIVE LOGITS
    </th>
    0.76
    리
    0.72
    myButtons
    0.71
    ције
    0.68
     backgroundImg
    0.66
    ্ল
    0.63
    ্লিক
    0.63
    "],
    0.62
     sanguin
    0.62
     permesso
    0.60
    Activations Density 0.029%

    No Known Activations