© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9576
    Prev
    Next
    INDEX
    Explanations

    if(!require(

    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
    <unused29>
    0.29
    Moz
    0.29
    moz
    0.28
    ણ
    0.27
     Trades
    0.26
    Trades
    0.26
     pad
    0.26
    SOS
    0.25
    ょ
    0.25
    째
    0.25
    POSITIVE LOGITS
    鴟
    0.29
     nonthermal
    0.29
     SELECTED
    0.29
    酺
    0.29
    сторі
    0.27
     പ്രവർത്തന
    0.27
    朢
    0.27
    غیر
    0.27
     Bedi
    0.26
    聑
    0.26
    Activations Density 0.002%

    No Known Activations