© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 131591
    Prev
    Next
    INDEX
    Explanations

    tariff

    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_50_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
    চনার
    0.35
    linson
    0.35
    ܢ
    0.34
    நாதன்
    0.34
     transplants
    0.34
    ्योपै
    0.34
     Kxc
    0.33
    anthe
    0.33
    lcii
    0.33
    浣
    0.33
    POSITIVE LOGITS
     Tar
    3.08
     tar
    3.06
    Tar
    3.05
     TAR
    2.83
    tar
    2.77
    TAR
    2.64
     Тар
    2.45
     tariff
    2.44
     Tariff
    2.41
     тар
    2.33
    Activations Density 0.001%

    No Known Activations