© 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. 128911
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and formulas

    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
    t
    1.48
    ing
    1.27
    es
    1.24
    h
    1.13
    f
    1.10
    and
    1.03
    g
    1.02
    cs
    1.01
    c
    1.00
    d
    0.98
    POSITIVE LOGITS
    та
    1.00
    の位置
    0.96
     temptations
    0.95
     diagonals
    0.95
    ु
    0.91
     burdensome
    0.90
    の話
    0.89
     fenders
    0.89
     canoes
    0.88
     hazelnuts
    0.88
    Activations Density 0.001%

    No Known Activations