© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 149343
    Prev
    Next
    INDEX
    Explanations

    written and created by

    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_18_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
    సా
    0.62
     Weib
    0.54
     Jé
    0.54
     Produkt
    0.54
    ْس
    0.54
    чва
    0.54
    耶稣
    0.51
     Produktion
    0.50
     aço
    0.50
    сения
    0.50
    POSITIVE LOGITS
     differentiable
    0.50
     timeline
    0.49
     formulating
    0.48
     deduce
    0.46
     scalability
    0.46
     pantry
    0.46
     &
    0.46
     reminiscent
    0.46
     docked
    0.46
     wrinkle
    0.45
    Activations Density 0.001%

    No Known Activations