© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26619
    Prev
    Next
    INDEX
    Explanations

    connectivity

    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_10_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
    硣
    0.71
     economía
    0.70
     ecuaciones
    0.68
     expliquer
    0.68
     geometría
    0.68
    ков
    0.68
    र्थिक
    0.66
    ]=[
    0.65
     átomos
    0.64
     але
    0.64
    POSITIVE LOGITS
    u
    1.09
    is
    1.02
    os
    0.95
    oi
    0.90
    r
    0.90
    ler
    0.88
    h
    0.86
    es
    0.85
    are
    0.85
    l
    0.83
    Activations Density 0.005%

    No Known Activations