© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9938
    Prev
    Next
    INDEX
    Explanations

    context.get

    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_13_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
     Ці
    0.56
     cellule
    0.54
    ﺹ
    0.51
    Off
    0.50
     данни
    0.50
     dehydrogen
    0.49
     cellules
    0.48
     ப்ளாக்
    0.48
    ர்க்
    0.47
     hücre
    0.47
    POSITIVE LOGITS
     Zhejiang
    0.63
     Yin
    0.59
     i
    0.57
    지
    0.57
     Bas
    0.55
    ع
    0.55
     Sony
    0.55
    akas
    0.55
     President
    0.52
    ید
    0.52
    Activations Density 0.003%

    No Known Activations