© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28500
    Prev
    Next
    INDEX
    Explanations

    the... better, cheaper, more, less

    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
    {
    0.68
    ires
    0.66
    $,
    0.62
     unfortunate
    0.54
    ，
    0.54
     exaggerated
    0.53
     unaware
    0.52
     because
    0.51
    ،
    0.51
    ਆਂ
    0.51
    POSITIVE LOGITS
    お金
    0.71
    お
    0.70
    ת
    0.69
    os
    0.66
    お客
    0.60
    Men
    0.59
     സീ
    0.59
    ت
    0.58
     பாம்பு
    0.57
    <unused749>
    0.57
    Activations Density 0.047%

    No Known Activations