© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 210937
    Prev
    Next
    INDEX
    Explanations

    Helen Graham; subjects; United States

    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_19_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
     is
    0.52
    ");*/
    0.45
    או
    0.45
    ی
    0.45
     isn
    0.44
     aka
    0.43
    ائج
    0.41
     Theological
    0.41
    ق
    0.41
    ц
    0.40
    POSITIVE LOGITS
     mécan
    0.51
     عزيز
    0.48
    சிக்கும்
    0.47
     जागरूक
    0.46
     Latham
    0.44
     وزار
    0.43
    维护
    0.43
     види
    0.43
    क्षी
    0.43
     প্রবাহ
    0.43
    Activations Density 0.000%

    No Known Activations