© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212433
    Prev
    Next
    INDEX
    Explanations

    jooq transactions or xargs commands

    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_5_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
    л
    0.94
    س
    0.90
    val
    0.89
    in
    0.87
    ha
    0.85
    ل
    0.85
    ه‌
    0.83
    st
    0.79
    ena
    0.79
    ction
    0.77
    POSITIVE LOGITS
     змі
    0.87
    ために
    0.82
     perdida
    0.82
     tranquila
    0.81
     passada
    0.80
     cambi
    0.79
     núcle
    0.79
     coexist
    0.79
     vontade
    0.79
     branca
    0.79
    Activations Density 0.001%

    No Known Activations