© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 134257
    Prev
    Next
    INDEX
    Explanations

    K

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Maiden
    0.40
    alk
    0.38
     हल्ला
    0.38
    matt
    0.36
     lớp
    0.36
     enact
    0.35
     alight
    0.35
    櫒
    0.35
     mayhem
    0.35
    cloak
    0.35
    POSITIVE LOGITS
     ste
    0.40
    árias
    0.40
     сте
    0.40
     impedances
    0.39
    Ari
    0.38
     ин
    0.38
     sü
    0.38
     ネ
    0.37
     resett
    0.37
    xE
    0.37
    Activations Density 0.001%

    No Known Activations