© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54922
    Prev
    Next
    INDEX
    Explanations

    duration or time

    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_55_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
     exposed
    0.40
     Exposed
    0.40
     amidst
    0.38
     highlighted
    0.38
     held
    0.37
     talked
    0.37
     amid
    0.36
     Как
    0.36
    吸
    0.36
     persuaded
    0.36
    POSITIVE LOGITS
    Shortly
    0.50
     shortly
    0.49
     hours
    0.48
    hours
    0.45
    Hours
    0.45
    extends
    0.40
    Bene
    0.40
     horas
    0.39
     ஏற்ப
    0.39
     Shortly
    0.39
    Activations Density 0.006%

    No Known Activations