© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92698
    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
    Why
    0.54
    Consider
    0.53
    Suggest
    0.53
    Viol
    0.51
    X
    0.49
    Cursor
    0.48
    د
    0.48
    Harga
    0.48
    Don
    0.48
    Hotel
    0.47
    POSITIVE LOGITS
     princípio
    0.54
     vadati
    0.52
     lãnh
    0.52
    ')$
    0.51
     തുടങ്ങ
    0.51
     ratification
    0.51
     ribbed
    0.50
     engages
    0.50
     tende
    0.50
     seguire
    0.50
    Activations Density 0.000%

    No Known Activations