© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232875
    Prev
    Next
    INDEX
    Explanations

    materials and circuits

    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_6_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
    的
    0.80
     on
    0.72
    、
    0.65
     thePack
    0.64
    硗
    0.63
     group
    0.62
     creek
    0.62
     checker
    0.61
    órico
    0.61
    ³.
    0.61
    POSITIVE LOGITS
    n
    1.27
    p
    1.01
    هم
    0.96
    c
    0.90
    ص
    0.88
    x
    0.85
    ci
    0.82
    k
    0.82
    cı
    0.79
    gi
    0.78
    Activations Density 0.035%

    No Known Activations