© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31989
    Prev
    Next
    INDEX
    Explanations

    mind and thoughts

    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_7_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
     gøre
    0.31
     lidí
    0.29
     zwart
    0.29
     органы
    0.28
    㗁
    0.28
     recicl
    0.28
     заня
    0.28
     tomto
    0.27
     нагрузки
    0.27
     sparen
    0.27
    POSITIVE LOGITS
    i
    0.41
    یم
    0.40
    ی
    0.39
    یت
    0.38
    تح
    0.34
    ۳
    0.34
    ना
    0.33
    𝗲
    0.32
    ين
    0.32
    ۲
    0.32
    Activations Density 0.010%

    No Known Activations