© 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. 248146
    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
    វា
    0.42
    oldsymbol
    0.39
    нную
    0.39
    outer
    0.38
    ileri
    0.38
    ver
    0.37
    ))));
    0.37
    triple
    0.36
    orge
    0.36
    )),
    0.36
    POSITIVE LOGITS
     prioritize
    0.40
     stuck
    0.39
     prioritizing
    0.38
     cle
    0.37
     পুর্ব
    0.37
    袮
    0.37
    cle
    0.35
     वर्चुअल
    0.35
     enslaved
    0.35
     clone
    0.34
    Activations Density 0.000%

    No Known Activations