© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 102952
    Prev
    Next
    INDEX
    Explanations

    undergraduate or graduate degree context

    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_1_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
    of
    1.59
    ק
    1.20
     of
    1.09
    вається
    1.02
    one
    1.02
     של
    0.99
    וף
    0.97
     ד
    0.96
     в
    0.95
     $
    0.95
    POSITIVE LOGITS
    ET
    1.28
    ut
    1.27
    কে
    1.26
    ED
    1.24
    ot
    1.20
    ur
    1.19
    OT
    1.17
    u
    1.16
    ER
    1.08
    IL
    1.07
    Activations Density 0.000%

    No Known Activations