© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90496
    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_11_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
    να
    0.57
    通常の
    0.56
    т
    0.55
    ー
    0.55
    ≥
    0.53
    θο
    0.52
    πος
    0.51
    уна
    0.51
    ucionales
    0.51
    ത്തിയ
    0.50
    POSITIVE LOGITS
    0.49
     ค
    0.48
     guiding
    0.47
     malzem
    0.46
     geest
    0.46
     discretion
    0.45
     küçük
    0.45
     lies
    0.44
     side
    0.44
     ballpark
    0.44
    Activations Density 0.000%

    No Known Activations