© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14166
    Prev
    Next
    INDEX
    Explanations

    Korean and Japanese language features

    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_13_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
     Suppose
    0.16
     Honestly
    0.16
     Required
    0.15
     conced
    0.15
    console
    0.15
    install
    0.15
     Pentru
    0.15
    璀
    0.14
     Gọi
    0.14
     niż
    0.14
    POSITIVE LOGITS
     он
    0.16
     этот
    0.16
    LLAR
    0.15
     обра
    0.15
     одного
    0.15
    štění
    0.15
     одной
    0.14
     dieses
    0.14
    ETY
    0.14
     அளவிற்கு
    0.14
    Activations Density 0.001%

    No Known Activations