© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205293
    Prev
    Next
    INDEX
    Explanations

    balance of payments deficit

    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_6_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
    ක්
    1.02
    ’
    0.98
    䍜
    0.98
    να
    0.98
    িন
    0.93
    ла
    0.93
    ول
    0.93
    న్
    0.93
    䟧
    0.93
    ющие
    0.91
    POSITIVE LOGITS
    t
    1.92
    s
    1.38
     are
    1.28
    i
    1.18
    ses
    1.17
    e
    1.09
    y
    1.09
     as
    1.07
    o
    0.96
    se
    0.88
    Activations Density 0.000%

    No Known Activations