© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61461
    Prev
    Next
    INDEX
    Explanations

    Interjections and names

    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_2_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
    的两
    1.09
    า
    1.03
    の両
    1.00
    的全
    0.99
    的面
    0.92
    ا
    0.92
    的這個
    0.90
    的行为
    0.90
    的书
    0.90
    的可
    0.90
    POSITIVE LOGITS
    '
    1.71
    \
    1.39
    D
    1.16
    "
    1.13
    W
    1.13
    0
    1.12
    R
    1.12
    4
    1.11
     it
    1.09
    M
    1.08
    Activations Density 0.001%

    No Known Activations