© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16104
    Prev
    Next
    INDEX
    Explanations

    model generating code

    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_40_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
    uchtung
    0.38
     occupational
    0.38
    urred
    0.36
    oum
    0.36
     passieren
    0.35
    doom
    0.35
    讲话
    0.35
     করতেই
    0.34
    搗
    0.34
     செய்த
    0.34
    POSITIVE LOGITS
     fellows
    0.87
     Fellows
    0.86
    Fellow
    0.69
     Fellowship
    0.66
     fellowship
    0.65
     Fellow
    0.64
     fellowships
    0.61
    fellow
    0.50
     fellow
    0.47
     FR
    0.42
    Activations Density 0.025%

    No Known Activations