© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 181366
    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_24_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
    o
    0.48
     southeastern
    0.46
     viewed
    0.46
    odt
    0.44
    ■
    0.43
    CTIONS
    0.43
    $-$
    0.43
     preclude
    0.42
     ASME
    0.42
    మ్‌
    0.41
    POSITIVE LOGITS
    regel
    0.51
    نگ
    0.44
     Mitigation
    0.43
    蒻
    0.43
    నించ
    0.40
     مرم
    0.40
     સ્ટ
    0.40
     Разби
    0.39
    langen
    0.39
     प्रतिनिधित्व
    0.38
    Activations Density 0.000%

    No Known Activations