© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 6967
    Prev
    Next
    INDEX
    Explanations

    peak state

    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_44_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
     содержи
    0.40
     obeyed
    0.38
     PYTHON
    0.38
    పోయ
    0.38
    根本
    0.38
     fieldContext
    0.37
    মুজিব
    0.37
    ('.',
    0.37
    ('.')[
    0.36
    OfInterest
    0.36
    POSITIVE LOGITS
     peak
    0.39
     Fre
    0.38
    Peak
    0.38
     actualizar
    0.38
     Peak
    0.37
    Fre
    0.37
    AGE
    0.36
     espiritual
    0.36
     sensit
    0.36
     mon
    0.35
    Activations Density 0.003%

    No Known Activations