© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4121
    Prev
    Next
    INDEX
    Explanations

    company / 工作 / 你 / your

    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_40_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
     эпо
    0.38
    Perform
    0.37
     мяс
    0.37
     gir
    0.36
     eius
    0.35
     éxitos
    0.35
    lägt
    0.34
    lux
    0.34
    繖
    0.34
     reprez
    0.33
    POSITIVE LOGITS
     company
    0.82
    公司
    0.79
    company
    0.79
     कंपनी
    0.71
    公司的
    0.70
    Company
    0.69
     회사
    0.68
     Company
    0.68
    회사
    0.66
    会社
    0.66
    Activations Density 0.030%

    No Known Activations