© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206002
    Prev
    Next
    INDEX
    Explanations

    | pipe operator

    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_20_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
    ’,
    0.25
    Nurse
    0.24
    汴
    0.23
    Chapters
    0.23
    ”)
    0.23
    роид
    0.23
    
    0.23
    ,’
    0.22
    ’)
    0.22
     পর্বে
    0.22
    POSITIVE LOGITS
     datang
    0.23
     mellem
    0.23
     veio
    0.23
     né
    0.22
    ρί
    0.21
    intai
    0.21
     Pasta
    0.21
     বাঁচাতে
    0.21
    vanje
    0.21
     "¿
    0.21
    Activations Density 0.003%

    No Known Activations