© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162561
    Prev
    Next
    INDEX
    Explanations

    orbs or barbs

    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_2_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
    ด
    1.88
    ال
    1.78
    ت
    1.71
    ב
    1.70
    ي
    1.55
    л
    1.52
    д
    1.52
    ৭
    1.41
    t
    1.37
    ل
    1.37
    POSITIVE LOGITS
    2
    1.30
    that
    0.95
    <0xBE>
    0.81
    informatics
    0.80
    textrm
    0.79
     отмети
    0.78
     됐
    0.77
    <0x91>
    0.76
     कै
    0.75
    ocrine
    0.75
    Activations Density 0.001%

    No Known Activations