© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173529
    Prev
    Next
    INDEX
    Explanations

    for you

    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_20_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
    垠
    0.52
    ▩
    0.50
    рис
    0.48
     destinés
    0.47
     villes
    0.46
    για
    0.46
    酈
    0.46
    λευτα
    0.46
    ૪
    0.45
    જન
    0.45
    POSITIVE LOGITS
    w
    0.55
    bar
    0.54
    t
    0.54
    (
    0.54
     and
    0.52
     l
    0.51
    ,
    0.50
    P
    0.50
     +
    0.49
    &
    0.49
    Activations Density 0.002%

    No Known Activations