© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102539
    Prev
    Next
    INDEX
    Explanations

    fees, tax, rates, income

    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_16_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
    be
    0.48
    নিজ
    0.48
    pou
    0.48
    aj
    0.46
    otek
    0.45
    APTER
    0.45
    ED
    0.44
    '=>$
    0.44
    పే
    0.44
    ajj
    0.44
    POSITIVE LOGITS
     фаразы
    0.48
    тни
    0.47
    δες
    0.46
    δου
    0.46
    щего
    0.46
     kesalahan
    0.45
     mischief
    0.45
     spy
    0.44
     वाहनों
    0.44
     două
    0.44
    Activations Density 0.000%

    No Known Activations