© 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. 89828
    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
     richtigen
    0.58
     Generate
    0.48
     richtige
    0.48
    сунок
    0.48
    滃
    0.47
    พอ
    0.47
     Quels
    0.47
    甘
    0.46
     Ergebnis
    0.46
     humains
    0.46
    POSITIVE LOGITS
    Ont
    0.53
     послед
    0.47
     means
    0.47
    ing
    0.46
     tras
    0.46
     lint
    0.45
     układ
    0.45
     یکی
    0.45
    нтов
    0.45
     приве
    0.45
    Activations Density 0.000%

    No Known Activations