© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43371
    Prev
    Next
    INDEX
    Explanations

    mcdonald's and mcnuggets

    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_3_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
    า
    0.88
    та
    0.76
    να
    0.73
    ס
    0.70
    ’,
    0.66
    ስ
    0.64
     सारी
    0.62
     значення
    0.62
     grafica
    0.62
     a
    0.61
    POSITIVE LOGITS
    h
    1.24
    f
    1.00
    ام
    0.87
    И
    0.84
    am
    0.82
    hok
    0.81
    М
    0.79
    de
    0.79
    ACK
    0.75
    Ř
    0.75
    Activations Density 0.000%

    No Known Activations