© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53278
    Prev
    Next
    INDEX
    Explanations

    names ending in "on", "le", "ino", "in", "a", "y", "rg", "worth"

    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_31_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
     chez
    0.35
     sé
    0.34
     Ud
    0.34
    輯
    0.34
     ex
    0.34
     vir
    0.34
     camp
    0.33
     Bou
    0.33
     mortal
    0.32
     سنت
    0.32
    POSITIVE LOGITS
     dépens
    0.39
    ทุก
    0.38
    ᱙
    0.37
     никогда
    0.37
     raind
    0.37
     لحظ
    0.36
     predmet
    0.36
     বাতাসে
    0.35
    来说
    0.35
    точные
    0.35
    Activations Density 0.011%

    No Known Activations