© 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. 79263
    Prev
    Next
    INDEX
    Explanations

    foreign/technical words

    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
    ंदाज
    0.38
    ိုင်
    0.37
    鋈
    0.37
     不是
    0.35
     Anders
    0.35
     Instrum
    0.35
     FACTORS
    0.34
     সিনেম
    0.34
     каком
    0.34
     বাতাস
    0.34
    POSITIVE LOGITS
     mathematicians
    0.36
    啵
    0.33
     tulle
    0.32
    ۇل
    0.32
    慗
    0.32
     brand
    0.32
     mee
    0.32
     fleur
    0.32
     producers
    0.32
    ienne
    0.32
    Activations Density 0.023%

    No Known Activations