© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 193775
    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_15_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
    <h2>
    0.64
     =
    0.55
     in
    0.54
    -
    0.54
    rance
    0.53
    El
    0.51
    \
    0.51
    Ace
    0.50
    ce
    0.49
    ái
    0.49
    POSITIVE LOGITS
    デル
    0.54
    鉗
    0.53
     datth
    0.52
    羋
    0.51
    ꩦ
    0.51
    </bbox>
    0.51
     CCOC
    0.51
     коюм
    0.50
     cakkh
    0.50
    ുപത്രി
    0.50
    Activations Density 0.000%

    No Known Activations