© 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. 87400
    Prev
    Next
    INDEX
    Explanations

    There

    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
     is
    0.99
    '
    0.72
     Is
    0.68
     has
    0.58
    Is
    0.52
     seems
    0.47
    is
    0.46
     Seems
    0.45
    는
    0.43
     हैव
    0.42
    POSITIVE LOGITS
     были
    0.71
    Were
    0.71
     were
    0.63
    were
    0.63
     تھے
    0.57
     були
    0.57
     Were
    0.57
     WERE
    0.56
     بودند
    0.55
     होंगी
    0.52
    Activations Density 0.001%

    No Known Activations