© 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. 262003
    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
    Ῥ
    0.50
    ആര്‍
    0.47
     rink
    0.47
    ેચ્છ
    0.47
     urination
    0.46
     individuality
    0.45
     inflammation
    0.44
     punkt
    0.44
     Corfu
    0.43
    etric
    0.43
    POSITIVE LOGITS
    都
    0.47
    원은
    0.46
     außer
    0.43
     testa
    0.43
    起到
    0.42
    ർച്ച
    0.42
     tová
    0.42
    يا
    0.42
    টো
    0.42
    야
    0.42
    Activations Density 0.000%

    No Known Activations