© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126175
    Prev
    Next
    INDEX
    Explanations

    GitHub links and associated information

    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_37_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
    ः
    0.42
     виртуа
    0.41
    ׃
    0.41
    ாய்ச்ச
    0.40
     TensorFlow
    0.39
     disponible
    0.39
    比特币
    0.38
     उपलब्धता
    0.38
    :
    0.38
    inelli
    0.37
    POSITIVE LOGITS
    ADDR
    0.46
     residence
    0.39
    NAME
    0.39
    ADDRESS
    0.38
     containing
    0.38
     path
    0.37
     stuffed
    0.37
    樂
    0.36
     NAME
    0.36
     crammed
    0.36
    Activations Density 0.004%

    No Known Activations