© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 79627
    Prev
    Next
    INDEX
    Explanations

    technical AI terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
     ያስፈል
    0.39
    ElementException
    0.38
    で行
    0.37
    分为
    0.36
     သည်
    0.36
    ">+</
    0.36
    被称为
    0.35
    ｢
    0.35
    便是
    0.35
    ować
    0.35
    POSITIVE LOGITS
     ...,
    0.38
     ..."
    0.36
    യും
    0.35
     ."
    0.35
     হয়তো
    0.35
     ..............
    0.34
     ...
    0.34
     .........
    0.34
     necessarily
    0.34
     darn
    0.34
    Activations Density 1.684%

    No Known Activations