© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113253
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     by
    1.17
    ーク
    0.96
     heralded
    0.96
    就开始
    0.94
    就把
    0.90
    就很
    0.90
    ?
    0.89
    യും
    0.89
     spearheaded
    0.89
     electrically
    0.88
    POSITIVE LOGITS
    n
    1.45
    ↵
    1.41
    di
    1.23
    dan
    1.23
    dra
    1.23
    del
    1.22
    t
    1.20
    make
    1.19
    お
    1.19
    la
    1.16
    Activations Density 0.000%

    No Known Activations