© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176759
    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_20_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
     capucha
    0.50
     അമേ
    0.47
    증
    0.47
     විශේෂ
    0.45
     restricciones
    0.45
    กัด
    0.43
     amarilla
    0.43
     hagy
    0.43
     الاسلام
    0.43
     사용자
    0.43
    POSITIVE LOGITS
    <0x80>
    0.49
    /-
    0.45
     müsste
    0.44
    /
    0.43
     soooo
    0.42
    $,
    0.41
     DSP
    0.41
     mehreren
    0.41
     Fell
    0.41
     became
    0.41
    Activations Density 0.000%

    No Known Activations