© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16759
    Prev
    Next
    INDEX
    Explanations

    economic and financial terms

    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_15_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
     І
    0.37
     corretamente
    0.34
     Ин
    0.33
     З
    0.33
     estrogens
    0.32
     Z
    0.31
    ໃນ
    0.31
     Этот
    0.31
     REQUIREMENTS
    0.31
    긁
    0.31
    POSITIVE LOGITS
    igen
    0.38
    mp
    0.37
    p
    0.37
    uten
    0.33
    ne
    0.32
    att
    0.30
    tter
    0.29
    v
    0.29
    atar
    0.29
    P
    0.29
    Activations Density 0.036%

    No Known Activations