© 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. 58548
    Prev
    Next
    INDEX
    Explanations

    nyan, -ite, -ian suffixes

    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
    م
    0.65
    as
    0.63
    ite
    0.63
     اكثر
    0.63
    劉
    0.62
    im
    0.60
    ählte
    0.59
    acaks
    0.59
    ars
    0.59
    acking
    0.58
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵
    0.54
     Cri
    0.52
     conquer
    0.52
     t
    0.51
     O
    0.50
     li
    0.50
     renormal
    0.50
     Il
    0.48
     h
    0.48
     Mogo
    0.48
    Activations Density 0.001%

    No Known Activations