© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19223
    Prev
    Next
    INDEX
    Explanations

    chartered accountants and public accountants

    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_15_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
     Goa
    0.57
    த்திற்க
    0.56
     Goo
    0.54
    或
    0.51
     ወይም
    0.51
    intermediate
    0.51
    𝙶
    0.51
     गोवा
    0.50
    டும்
    0.50
     ਜਾਂ
    0.50
    POSITIVE LOGITS
     currency
    0.58
     chronology
    0.55
     ataxia
    0.55
     insolvency
    0.54
     moneda
    0.53
     ketone
    0.53
     chipset
    0.52
     ललित
    0.52
     SOURCE
    0.51
    ل
    0.50
    Activations Density 0.000%

    No Known Activations