© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41951
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_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
     имат
    0.27
     পরিস্কার
    0.25
     tenían
    0.23
     liquef
    0.23
     мають
    0.23
     nosso
    0.23
    艿
    0.22
    ຽ
    0.22
     ngang
    0.22
     కలిసి
    0.21
    POSITIVE LOGITS
    1
    0.25
    9
    0.25
    owo
    0.25
     Sitemap
    0.24
    elmi
    0.24
     Dla
    0.23
     Now
    0.23
    ඕ
    0.23
     प्लांट्स
    0.23
    8
    0.23
    Activations Density 0.000%

    No Known Activations