© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28285
    Prev
    Next
    INDEX
    Explanations

    number of bedrooms

    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_40_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
     lived
    0.51
    lived
    0.48
     تعداد
    0.43
     жил
    0.43
    住在
    0.42
    住
    0.42
     cheaper
    0.42
     кількість
    0.41
     vivre
    0.41
     number
    0.41
    POSITIVE LOGITS
     famili
    0.37
     unlocked
    0.37
    🌻
    0.35
    miyor
    0.35
     المجلس
    0.34
    电子邮件
    0.33
     EMAIL
    0.33
    λος
    0.33
    宥
    0.33
    Letter
    0.33
    Activations Density 0.002%

    No Known Activations