© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 203745
    Prev
    Next
    INDEX
    Explanations

    articles and quantifiers in many languages

    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_25_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
     Joaquim
    0.33
    覷
    0.32
    ем
    0.32
    टा
    0.32
     ಬು
    0.31
    上記の
    0.31
    stud
    0.30
    鐫
    0.30
     procurar
    0.29
     numArray
    0.29
    POSITIVE LOGITS
     sobald
    0.38
     hver
    0.36
     jeder
    0.36
     ONE
    0.35
     trabalho
    0.35
     काही
    0.34
     fiecare
    0.33
     qualidade
    0.33
     всеки
    0.33
     Appalachian
    0.33
    Activations Density 0.025%

    No Known Activations