© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229547
    Prev
    Next
    INDEX
    Explanations

    multi-lingual conjunctions and particles

    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_6_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
    D
    1.13
    d
    1.09
    r
    1.05
    st
    0.97
    س
    0.96
     to
    0.91
    ב
    0.90
    л
    0.89
    t
    0.87
    z
    0.87
    POSITIVE LOGITS
    的表现
    0.83
    ти
    0.83
    的
    0.82
    ის
    0.80
    iteten
    0.77
    ്ട
    0.76
    च्या
    0.75
     казни
    0.75
     може
    0.75
     BlueprintName
    0.75
    Activations Density 0.000%

    No Known Activations