© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129092
    Prev
    Next
    INDEX
    Explanations

    writable

    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_1_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ر
    1.45
    ل
    1.37
     geomagnetic
    1.15
    >
    1.14
    нні
    1.12
    rú
    1.10
    rith
    1.09
    4
    1.05
    ４
    1.00
    며
    0.99
    POSITIVE LOGITS
     a
    1.38
    า
    1.09
    ين
    1.08
    ı
    1.00
    ah
    0.99
    la
    0.99
    dalam
    0.93
    <0x80>
    0.88
    doi
    0.88
    ا
    0.86
    Activations Density 0.000%

    No Known Activations