© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 87435
    Prev
    Next
    INDEX
    Explanations

    P

    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_60_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
     pillar
    2.44
     pillars
    2.39
     Pillars
    2.27
     Pillar
    2.11
    pillars
    2.06
    pillar
    2.00
    柱
    1.61
     পিলার
    1.19
     Pilar
    1.15
     স্তম্ভ
    0.95
    POSITIVE LOGITS
     p
    1.16
    P
    0.89
     प
    0.70
     پ
    0.70
    ｐ
    0.58
    PA
    0.54
    p
    0.54
     P
    0.54
     প
    0.53
    PO
    0.51
    Activations Density 0.001%

    No Known Activations