© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 65071
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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_51_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
     States
    0.39
     Compl
    0.39
     $(*
    0.38
     "'"
    0.38
    =".
    0.37
     cüm
    0.37
    \(
    0.37
     なかっ
    0.37
     Goo
    0.37
    icker
    0.37
    POSITIVE LOGITS
     Ã
    0.85
    Ã
    0.75
    ί
    0.75
    ά
    0.71
     piu
    0.68
    έ
    0.66
    ӕ
    0.65
     opcoes
    0.63
     ลํา
    0.62
     ทํา
    0.61
    Activations Density 0.094%

    No Known Activations