© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83426
    Prev
    Next
    INDEX
    Explanations

    deregistration, deregulated, dereference

    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_0_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
    した
    1.57
     in
    1.52
    p
    1.52
    _
    1.51
    kan
    1.46
     to
    1.36
    st
    1.36
    人
    1.31
    book
    1.30
    ku
    1.25
    POSITIVE LOGITS
    т
    1.85
    го
    1.51
    ت
    1.50
    فی
    1.46
     débil
    1.46
    ਰ
    1.45
    های
    1.43
    ру
    1.39
    یم
    1.38
    بھی
    1.37
    Activations Density 0.000%

    No Known Activations