© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 195799
    Prev
    Next
    INDEX
    Explanations

    do

    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_26_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
     করবে
    0.27
     paraphernalia
    0.27
    ⟦
    0.27
     thumbnailUrl
    0.26
     изготовления
    0.26
     enterprising
    0.26
     книг
    0.25
     소재
    0.25
    綗
    0.25
     opera
    0.25
    POSITIVE LOGITS
     முறையாக
    0.29
     disrespect
    0.27
    相手
    0.26
     podem
    0.26
     చర్య
    0.25
    ريكية
    0.25
    Calls
    0.24
     duly
    0.24
    意识到
    0.24
    ጊ
    0.24
    Activations Density 0.007%

    No Known Activations