© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50340
    Prev
    Next
    INDEX
    Explanations

    greetings like hi and hey

    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_10_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
    im
    0.98
    il
    0.90
    ين
    0.89
    í
    0.87
    :
    0.86
    i
    0.83
    ي
    0.82
    é
    0.79
    os
    0.77
    z
    0.77
    POSITIVE LOGITS
    К
    0.85
    dengan
    0.81
    Б
    0.80
    Бе
    0.75
    Ре
    0.74
    \}$
    0.73
     Не
    0.73
    Не
    0.72
     کامیاب
    0.72
    1
    0.72
    Activations Density 0.000%

    No Known Activations