© 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. 91873
    Prev
    Next
    INDEX
    Explanations

    learning materials

    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
    0.91
    ↵↵
    0.85
    é
    0.70
    z
    0.65
    ne
    0.64
    ”)
    0.63
    ↵↵↵
    0.62
    for
    0.61
    st
    0.59
     be
    0.58
    POSITIVE LOGITS
    یان
    0.72
    자가
    0.70
     terceros
    0.69
    る
    0.65
     horario
    0.64
    ක්
    0.63
    تين
    0.63
     internas
    0.61
     trabajar
    0.61
     صہی
    0.61
    Activations Density 0.008%

    No Known Activations