© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76795
    Prev
    Next
    INDEX
    Explanations

    Russian financial and business terms

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ရှိ
    0.33
    지
    0.33
     Registered
    0.32
     Psychic
    0.31
     internalType
    0.31
     mùa
    0.30
    Registered
    0.30
     cuch
    0.30
     ရှိ
    0.30
    仴
    0.29
    POSITIVE LOGITS
     finans
    0.33
    men
    0.31
     diplomat
    0.30
     reb
    0.30
     финанси
    0.30
     financiar
    0.29
    牽
    0.29
     листо
    0.29
    ‾
    0.29
     financiación
    0.28
    Activations Density 0.002%

    No Known Activations