© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57999
    Prev
    Next
    INDEX
    Explanations

    accumulate, accumulating, accumulated

    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_11_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
    ين
    0.38
    स्टिव
    0.37
     আগেও
    0.35
    african
    0.34
     न्यायिक
    0.34
    ку
    0.34
     african
    0.34
    n
    0.33
     অনুষ্ঠ
    0.32
     অবজারভার
    0.32
    POSITIVE LOGITS
    ↵
    0.39
    نی
    0.29
     que
    0.29
    0.28
     repulsive
    0.28
    #
    0.28
    ه‌ای
    0.27
     polarity
    0.27
     dart
    0.27
    mathrm
    0.27
    Activations Density 0.004%

    No Known Activations