© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226917
    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_10_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
    otur
    0.51
    ющих
    0.49
    <0x91>
    0.49
    urals
    0.48
     monochrom
    0.46
     solidly
    0.44
    ν
    0.44
    ью
    0.44
    (
    0.44
    oblast
    0.43
    POSITIVE LOGITS
    𝙋
    0.59
    𝗛
    0.53
    𝗚
    0.52
    לה
    0.51
    la
    0.51
    Orden
    0.50
     and
    0.49
    รก
    0.48
     ನಿಮ್ಮ
    0.48
    🅽
    0.48
    Activations Density 0.000%

    No Known Activations