© 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. 33440
    Prev
    Next
    INDEX
    Explanations

    app titles

    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
     for
    0.75
     by
    0.64
     and
    0.59
     et
    0.59
     mania
    0.59
     reve
    0.58
     parecido
    0.57
     API
    0.57
     dica
    0.56
     &&
    0.55
    POSITIVE LOGITS
    ба
    0.69
    s
    0.69
    q
    0.69
    to
    0.68
    ра
    0.68
    ের
    0.67
    k
    0.66
    с
    0.66
    j
    0.62
    ও
    0.61
    Activations Density 0.005%

    No Known Activations