© 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. 135543
    Prev
    Next
    INDEX
    Explanations

    recognized for their

    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
    L
    1.73
    S
    1.66
    N
    1.55
    B
    1.52
    D
    1.45
    J
    1.42
    H
    1.41
    P
    1.41
    ال
    1.39
    U
    1.39
    POSITIVE LOGITS
    dine
    0.90
     교통
    0.90
    ried
    0.88
    aking
    0.84
    eller
    0.84
    ettes
    0.81
     경로
    0.81
     후
    0.80
     데
    0.80
    age
    0.80
    Activations Density 0.001%

    No Known Activations