© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198098
    Prev
    Next
    INDEX
    Explanations

    commercial vehicles and delivery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_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
    )}}
    0.55
    )."
    0.54
     ASA
    0.54
    いろいろ
    0.53
    帏
    0.53
     archi
    0.52
     enige
    0.51
     มัน
    0.51
     செய்
    0.51
     Fair
    0.50
    POSITIVE LOGITS
    es
    0.65
    𝗮
    0.60
    𝗹
    0.60
    ap
    0.60
    ف
    0.59
    l
    0.58
    an
    0.57
    𝘇
    0.57
    p
    0.57
    f
    0.57
    Activations Density 0.000%

    No Known Activations