© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35517
    Prev
    Next
    INDEX
    Explanations

    URLs, .com, .org

    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_11_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
     नाग
    0.51
    ో
    0.50
     shutil
    0.49
     сосе
    0.49
    tuvo
    0.48
    IGE
    0.47
    ir
    0.47
     wizards
    0.47
    🧉
    0.45
     отсутствует
    0.45
    POSITIVE LOGITS
     of
    0.51
     Trần
    0.49
    ously
    0.48
    ﺒ
    0.47
    щего
    0.47
    antly
    0.46
     l
    0.45
    creational
    0.45
    ently
    0.45
    рами
    0.44
    Activations Density 0.000%

    No Known Activations