© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179938
    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_24_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
     lur
    0.58
     souhait
    0.54
     lurking
    0.52
     茶
    0.51
     deux
    0.50
    \}$.
    0.49
    ゥム
    0.49
     Hasbro
    0.48
    簀
    0.48
     placard
    0.48
    POSITIVE LOGITS
    الأ
    0.50
    K
    0.50
    Defense
    0.49
    А
    0.49
    Rescue
    0.48
    Б
    0.46
    Wild
    0.46
    Ł
    0.46
    Для
    0.46
    Pou
    0.46
    Activations Density 0.000%

    No Known Activations