© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35369
    Prev
    Next
    INDEX
    Explanations

    UK 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_31_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
     deli
    0.45
     Deli
    0.42
     زي
    0.39
     Italian
    0.37
    )|^{
    0.36
    养
    0.36
     check
    0.36
    Delimiter
    0.36
     खाते
    0.35
     Mish
    0.35
    POSITIVE LOGITS
    vene
    0.39
    Rota
    0.38
    Lead
    0.37
    酴
    0.37
    poem
    0.37
     WORTH
    0.36
    metal
    0.36
    shear
    0.35
    sker
    0.35
    sugar
    0.35
    Activations Density 0.017%

    No Known Activations