© 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. 46990
    Prev
    Next
    INDEX
    Explanations

    server-side or client-side

    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
    ното
    0.62
    ้น
    0.54
    0.52
    ้
    0.52
    на
    0.51
    دة
    0.50
    ност
    0.49
    다
    0.48
     dne
    0.47
    наче
    0.47
    POSITIVE LOGITS
     side
    0.74
    Side
    0.64
     Side
    0.64
     lados
    0.62
    SIDE
    0.62
    ၡ
    0.61
    ut
    0.59
     SIDE
    0.58
    h
    0.56
    <
    0.56
    Activations Density 0.019%

    No Known Activations