© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17158
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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
     Wet
    0.32
     wet
    0.29
    借
    0.29
     borrow
    0.28
     beste
    0.27
     Pompe
    0.27
     chained
    0.27
    epte
    0.27
    原子
    0.27
    ount
    0.26
    POSITIVE LOGITS
    GRO
    0.38
     mascara
    0.35
    Winters
    0.31
     니
    0.30
    िक्
    0.29
    Peri
    0.29
    Вели
    0.29
    Gro
    0.29
     churches
    0.29
    хол
    0.29
    Activations Density 0.001%

    No Known Activations