© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15282
    Prev
    Next
    INDEX
    Explanations

    business logic

    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_40_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
     mole
    0.41
    genomes
    0.40
     Mole
    0.39
    옻
    0.35
     *$
    0.34
     derivada
    0.33
    brook
    0.33
     mysqli
    0.33
    TestCase
    0.33
    ភ្
    0.33
    POSITIVE LOGITS
     logic
    3.13
    logic
    2.77
     Logic
    2.73
    Logic
    2.70
    逻辑
    2.55
     lógica
    2.44
     logics
    2.42
    邏
    2.34
     logique
    2.20
     logika
    2.19
    Activations Density 0.147%

    No Known Activations