© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153061
    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_23_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
     एंटीऑ
    0.41
    Prefix
    0.40
    
    0.40
     α
    0.39
     leaky
    0.39
     lạnh
    0.38
    よね
    0.38
     leak
    0.37
    =?
    0.37
     leaked
    0.37
    POSITIVE LOGITS
    法轮
    0.40
    altung
    0.38
    weil
    0.38
    ichtung
    0.37
    plc
    0.37
     abaste
    0.37
     Ayer
    0.37
    pt
    0.36
    基督教
    0.36
    घरों
    0.36
    Activations Density 0.000%

    No Known Activations