© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 94133
    Prev
    Next
    INDEX
    Explanations

    economy

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    f
    0.88
    c
    0.54
    omic
    0.52
     manages
    0.48
    st
    0.47
    ex
    0.46
    omy
    0.46
    j
    0.46
    omics
    0.46
     handling
    0.45
    POSITIVE LOGITS
     improve
    0.53
    improve
    0.52
     Improve
    0.51
     cải
    0.51
     enhance
    0.47
    MSFont
    0.44
    enhance
    0.42
    Improve
    0.41
    UIControl
    0.41
    ície
    0.40
    Activations Density 0.000%

    No Known Activations