© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29934
    Prev
    Next
    INDEX
    Explanations

    occupation and salary

    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_10_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
     七
    0.28
     étaient
    0.26
    ్‌
    0.25
     كانت
    0.25
     学校
    0.25
    考核
    0.25
    数据
    0.25
     były
    0.25
    当时
    0.24
    ští
    0.24
    POSITIVE LOGITS
    נות
    0.28
    m
    0.28
    named
    0.27
    ns
    0.27
     installment
    0.27
     a
    0.26
    analytic
    0.25
    נים
    0.25
    timer
    0.25
    anks
    0.25
    Activations Density 0.071%

    No Known Activations