© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42162
    Prev
    Next
    INDEX
    Explanations

    outdoor dining, living, kitchen, cooking

    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_3_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
    k
    1.27
    d
    1.08
    b
    1.07
    in
    1.02
    z
    1.02
    p
    1.00
    m
    0.99
    g
    0.90
    s
    0.89
    al
    0.86
    POSITIVE LOGITS
    ৪
    0.83
    ﺔ
    0.77
     aliqua
    0.76
    ای
    0.75
     eleições
    0.75
     accéder
    0.74
    ۸
    0.74
    ５
    0.74
    ೪
    0.72
     reacciones
    0.72
    Activations Density 0.000%

    No Known Activations