© 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
    2. Gemma-3-27B-IT
    3. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 234302
    Prev
    Next
    INDEX
    Explanations

    balancing

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    ೇಕ
    0.39
    蜮
    0.37
    勒
    0.36
    μό
    0.35
     ചെറു
    0.35
    ശ്വാ
    0.34
    ्रु
    0.34
     Proctor
    0.34
    tion
    0.34
    佈
    0.34
    POSITIVE LOGITS
     balance
    3.48
     balancing
    3.23
     Balance
    3.17
     балан
    3.14
    balance
    3.13
    Balance
    3.05
     balances
    3.05
     Balancing
    2.92
    balancing
    2.80
    バランス
    2.77
    Activations Density 0.306%

    No Known Activations