© 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. 149804
    Prev
    Next
    INDEX
    Explanations

    location words

    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
    Not in Any Lists

    No Comments

    Negative Logits
     e
    0.54
     rapidly
    0.48
     continuously
    0.48
     slowly
    0.44
     steadily
    0.41
     rapidamente
    0.41
    龰
    0.39
    ÁN
    0.39
    SDAY
    0.39
    ście
    0.39
    POSITIVE LOGITS
     где
    0.81
     donde
    0.80
     Letter
    0.78
     where
    0.76
     letra
    0.75
     lettre
    0.75
     letters
    0.74
     letras
    0.73
     lettres
    0.71
     Letters
    0.71
    Activations Density 0.000%

    No Known Activations