© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39589
    Prev
    Next
    INDEX
    Explanations

    organizing

    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
    T
    0.62
    Н
    0.60
    І
    0.59
     n
    0.57
    <0x0D>
    0.57
    Princess
    0.55
    ‌تر
    0.55
    6
    0.55
    Youtube
    0.54
     н
    0.54
    POSITIVE LOGITS
    㿝
    0.60
     trúc
    0.57
    يطان
    0.56
    ânica
    0.55
    imientos
    0.54
    ыска
    0.54
     கல்விய
    0.53
    ánico
    0.53
    ों
    0.51
    arcía
    0.51
    Activations Density 0.006%

    No Known Activations