© 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. 92850
    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
    Locked
    0.51
    部門
    0.51
    ਲ
    0.47
    Ordered
    0.46
    رفه
    0.45
    kého
    0.44
    roomId
    0.44
    জেলা
    0.44
    䡉
    0.44
    LOOP
    0.44
    POSITIVE LOGITS
     Bot
    0.49
     blessing
    0.47
     stead
    0.47
    resión
    0.47
    t
    0.47
    ty
    0.47
     Gesundheit
    0.46
     horribly
    0.45
     greeting
    0.45
    phen
    0.45
    Activations Density 0.000%

    No Known Activations