© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 203854
    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_56_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
    GYPT
    0.39
     AC
    0.37
     Sénégal
    0.35
    参
    0.35
    iconductor
    0.35
     Thumbnail
    0.35
    thom
    0.35
    原来的
    0.35
     completely
    0.34
     দৌড়ে
    0.34
    POSITIVE LOGITS
    𖤐
    0.40
    Few
    0.38
     svjets
    0.38
     kiles
    0.38
     размещения
    0.37
    แต
    0.37
    гле
    0.37
     relish
    0.37
     crave
    0.36
     euph
    0.36
    Activations Density 0.000%

    No Known Activations