© 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. 38702
    Prev
    Next
    INDEX
    Explanations

    Mc followed by Brain

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     года
    0.63
    Để
    0.62
    V
    0.61
    ou
    0.61
    Почему
    0.61
    Aunque
    0.60
    ом
    0.60
    ів
    0.59
    و
    0.58
    years
    0.56
    POSITIVE LOGITS
     rhyme
    0.61
     maximus
    0.61
    什么的
    0.60
     titt
    0.59
     whatnot
    0.59
     jel
    0.58
    clair
    0.58
     mondo
    0.58
     Gianni
    0.57
     ابراہیم
    0.57
    Activations Density 0.039%

    No Known Activations