© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 59139
    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
     ঘোষণ
    0.48
    閬
    0.47
    у
    0.46
     Retour
    0.45
     Accounts
    0.44
     мире
    0.44
    slick
    0.44
    破坏
    0.44
     Рей
    0.44
     Abgerufen
    0.44
    POSITIVE LOGITS
    N
    0.55
     or
    0.54
     on
    0.50
     legisl
    0.49
     expir
    0.47
     ሳይ
    0.46
     یا
    0.45
     꾸
    0.45
    D
    0.44
    Dial
    0.44
    Activations Density 0.000%

    No Known Activations