© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62778
    Prev
    Next
    INDEX
    Explanations

    occupy

    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_59_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ną
    0.62
    rz
    0.39
     przyj
    0.38
    :`
    0.36
     arah
    0.35
    𝗨
    0.35
    ampilan
    0.35
    順番
    0.35
    itol
    0.35
     straight
    0.34
    POSITIVE LOGITS
     zaj
    0.77
    occup
    0.52
     ocupar
    0.51
     Occup
    0.50
     przyn
    0.50
     занима
    0.48
     occupying
    0.48
     occupational
    0.48
    Occup
    0.48
    佔
    0.47
    Activations Density 0.004%

    No Known Activations