© 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. 57840
    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
    čių
    0.48
    ند
    0.47
    }$=
    0.47
    clients
    0.46
     공간
    0.45
    મ
    0.45
    너지
    0.45
    space
    0.44
    ısı
    0.44
    م
    0.44
    POSITIVE LOGITS
     applauded
    0.50
     admired
    0.48
     departed
    0.47
     departs
    0.46
     artillery
    0.45
     paralelo
    0.45
     alternates
    0.45
     ár
    0.44
     merely
    0.44
     básicos
    0.44
    Activations Density 0.000%

    No Known Activations