© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89428
    Prev
    Next
    INDEX
    Explanations

    background-color: #f0f0f0;

    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_23_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
    ேட்
    0.41
     setor
    0.40
     restaurantes
    0.39
     securities
    0.39
    <0xD1>
    0.39
     지원
    0.39
     ресторан
    0.38
    extends
    0.38
     plaza
    0.37
     investimentos
    0.37
    POSITIVE LOGITS
     આજ
    0.41
     χωρίς
    0.40
     January
    0.40
    慝
    0.39
     Sou
    0.38
    それが
    0.38
    Tou
    0.37
    確定
    0.37
     Hispan
    0.37
    Wikimedia
    0.37
    Activations Density 0.001%

    No Known Activations