© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207811
    Prev
    Next
    INDEX
    Explanations

    look for products

    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
    ู
    0.30
    储
    0.30
     आढळ
    0.28
     வீ
    0.28
    ligen
    0.27
     रुग्ण
    0.27
     রাজনৈতিক
    0.27
    病
    0.26
    の下
    0.26
    甴
    0.26
    POSITIVE LOGITS
     TreeSet
    0.30
    hita
    0.29
     celebrar
    0.28
     pca
    0.28
     ըն
    0.28
     brut
    0.27
     Chaotic
    0.27
     KMeans
    0.27
    சிக்கும்
    0.27
     Climb
    0.26
    Activations Density 0.019%

    No Known Activations