© 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. 9985
    Prev
    Next
    INDEX
    Explanations

    Taal, Doraemon, Chavacano, telenovela

    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
    ଆ
    0.46
    एक
    0.39
     surrounds
    0.38
    ාවක්
    0.38
    вій
    0.36
    wegs
    0.33
     nút
    0.33
     वेग
    0.33
    飞机
    0.33
    अप
    0.33
    POSITIVE LOGITS
    ﻠ
    0.39
    XPATH
    0.38
     रेजि
    0.38
    يدة
    0.37
    "،
    0.37
    DropDownList
    0.37
     résumé
    0.36
    LECTION
    0.36
    Bor
    0.36
    subheader
    0.36
    Activations Density 0.006%

    No Known Activations