© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33217
    Prev
    Next
    INDEX
    Explanations

    inet network headers

    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_3_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
    াদেশিক
    0.68
    IZONTAL
    0.63
     projective
    0.62
     postulated
    0.62
    dracht
    0.61
     variété
    0.61
    t
    0.61
     Пет
    0.60
     practical
    0.60
     hypnosis
    0.60
    POSITIVE LOGITS
    ى
    1.20
    يق
    1.05
    يش
    1.05
    f
    0.98
    as
    0.94
    ing
    0.93
    ص
    0.92
    is
    0.91
    الم
    0.89
    ين
    0.88
    Activations Density 0.007%

    No Known Activations