© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6024
    Prev
    Next
    INDEX
    Explanations

    Federal Reserve actions

    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_39_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
    }}}=\
    0.41
    éro
    0.40
     karyawan
    0.40
    Profiler
    0.38
     Hidalgo
    0.38
     transformada
    0.38
    bley
    0.38
     Racer
    0.37
    --',
    0.37
    ikr
    0.36
    POSITIVE LOGITS
     Fed
    0.90
    Federal
    0.84
    Fed
    0.84
     Federal
    0.83
     FEDERAL
    0.69
     FED
    0.66
     Федера
    0.65
     फेड
    0.63
     Reserve
    0.62
    FEDERAL
    0.61
    Activations Density 0.059%

    No Known Activations