© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39202
    Prev
    Next
    INDEX
    Explanations

    afterglow of

    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
    (
    0.82
    I
    0.79
    N
    0.78
    {
    0.74
    ({\
    0.73
    t
    0.73
     \
    0.72
    (,
    0.71
    ({
    0.69
    {//
    0.69
    POSITIVE LOGITS
    ні
    0.85
    ных
    0.80
    </h3>
    0.76
    ุ
    0.76
    ка
    0.74
    ों
    0.72
    </h2>
    0.71
    िक
    0.71
    sa
    0.71
    ки
    0.71
    Activations Density 0.000%

    No Known Activations