© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143767
    Prev
    Next
    INDEX
    Explanations

    segunda ley, segunda línea, segunda guerra

    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_0_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
    that
    2.38
    1
    1.99
     that
    1.88
    。
    1.59
    M
    1.42
    th
    1.39
    to
    1.39
    ।
    1.38
    R
    1.36
    ’
    1.34
    POSITIVE LOGITS
    ل
    2.34
    ри
    2.00
    ના
    1.75
    い
    1.63
    ल
    1.62
    л
    1.51
    大
    1.50
    ラック
    1.49
    માં
    1.48
    ون
    1.45
    Activations Density 0.000%

    No Known Activations