© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30390
    Prev
    Next
    INDEX
    Explanations

    company perks and benefits

    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_31_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
     Trench
    0.54
    speeds
    0.38
    barn
    0.38
    ín
    0.38
     barn
    0.36
     trench
    0.36
     speeds
    0.36
    Employees
    0.36
     Excav
    0.36
    =|
    0.36
    POSITIVE LOGITS
     hormones
    0.41
     yoga
    0.38
     klien
    0.38
    atars
    0.37
     jual
    0.37
     exercise
    0.37
     beaux
    0.37
     spandex
    0.37
     Pooja
    0.36
     찬
    0.36
    Activations Density 0.005%

    No Known Activations