© 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. 127974
    Prev
    Next
    INDEX
    Explanations

    endophthalmitis, endoplasmic, title, stand out

    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
    л
    0.82
    র্মে
    0.75
    д
    0.73
    ਾਂ
    0.69
    ل
    0.69
    м
    0.68
     Пред
    0.68
    hā
    0.66
    𝕝
    0.66
     Trabal
    0.65
    POSITIVE LOGITS
    i
    1.20
    ו
    1.14
    y
    1.06
    s
    0.93
    י
    0.91
    e
    0.85
    -
    0.80
    k
    0.77
    iencia
    0.77
    n
    0.77
    Activations Density 0.000%

    No Known Activations