© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63089
    Prev
    Next
    INDEX
    Explanations

    File

    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_46_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
     no
    0.47
     পরিবর্তন
    0.41
    ufieurs
    0.41
    扉
    0.40
    Ϟ
    0.38
    ện
    0.37
     nessun
    0.37
    駑
    0.36
    قسم
    0.36
     природы
    0.36
    POSITIVE LOGITS
     html
    0.39
    toa
    0.38
    kes
    0.38
     यार
    0.38
     mee
    0.38
     iss
    0.37
     bani
    0.37
    ved
    0.37
     ID
    0.37
     drawbacks
    0.37
    Activations Density 0.001%

    No Known Activations