© 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. 33687
    Prev
    Next
    INDEX
    Explanations

    freelance work platforms

    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
     hired
    0.64
     hire
    0.56
     hiring
    0.54
    Hire
    0.52
     hires
    0.50
     Hire
    0.49
     freelance
    0.48
     Hiring
    0.48
    Freel
    0.47
    僱
    0.46
    POSITIVE LOGITS
     रोकना
    0.38
    ಾಗುತ್ತದೆ
    0.37
    साइट
    0.36
     aap
    0.36
    xadmin
    0.35
    enaire
    0.35
    दाना
    0.35
     Aap
    0.35
     वेबसाईट
    0.35
    ждане
    0.34
    Activations Density 0.002%

    No Known Activations