© 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. 50319
    Prev
    Next
    INDEX
    Explanations

    business glossary

    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
    matis
    0.31
    骥
    0.29
     уста
    0.28
    开发
    0.27
     ενη
    0.27
     किसान
    0.27
     Jira
    0.27
    撵
    0.27
    遗
    0.27
    惋
    0.27
    POSITIVE LOGITS
    nelle
    0.28
     சப
    0.28
     accruing
    0.28
     qualifications
    0.28
     payable
    0.28
     ISBN
    0.27
     vows
    0.27
    湊
    0.27
    ῇ
    0.27
     ventric
    0.27
    Activations Density 0.000%

    No Known Activations