© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122854
    Prev
    Next
    INDEX
    Explanations

    Ambassador or diplomat

    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_37_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
    '%
    0.45
    恐
    0.39
    "%
    0.38
    掻
    0.38
     '%
    0.36
     \"%
    0.36
     %``
    0.36
    Commission
    0.35
    番
    0.35
    Hans
    0.35
    POSITIVE LOGITS
     Honduras
    0.40
     unserer
    0.39
    irce
    0.39
     recalls
    0.38
     çık
    0.38
     Blum
    0.37
     Sudan
    0.37
     Blogger
    0.37
     ihres
    0.37
     gan
    0.36
    Activations Density 0.000%

    No Known Activations