© 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. 209025
    Prev
    Next
    INDEX
    Explanations

    Vital

    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_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
    ractable
    0.34
    诒
    0.34
    冲
    0.33
    𝐲
    0.33
    敞
    0.32
     Mifflin
    0.32
     কন্
    0.32
    乸
    0.32
     trùng
    0.31
    धारण
    0.31
    POSITIVE LOGITS
     vit
    3.33
     Vit
    3.11
    Vit
    3.06
    vit
    2.97
     Vital
    2.83
    Vital
    2.83
     vital
    2.80
     VIT
    2.80
    vital
    2.67
    VIT
    2.59
    Activations Density 0.042%

    No Known Activations