© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52816
    Prev
    Next
    INDEX
    Explanations

    Myanmar, Galatians, Enhancements

    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_31_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
    hém
    0.39
    丁
    0.38
     hostess
    0.37
    原始内容存档
    0.36
     Ding
    0.36
     Gewer
    0.35
     centerline
    0.35
     Furnace
    0.34
     ACL
    0.33
    onavírus
    0.32
    POSITIVE LOGITS
    लट्
    0.41
    слі
    0.39
    芨
    0.39
     récol
    0.39
    sig
    0.38
    蓖
    0.38
     Conexion
    0.38
    hika
    0.37
    Probe
    0.37
     теории
    0.37
    Activations Density 0.000%

    No Known Activations