© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12805
    Prev
    Next
    INDEX
    Explanations

    retail and shopping locations

    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
     independent
    0.42
    3
    0.40
     Independent
    0.38
     independiente
    0.38
    0.37
     ,
    0.36
     indépend
    0.36
    (
    0.36
     independents
    0.35
     ott
    0.34
    POSITIVE LOGITS
     हाम्रो
    0.43
     theſe
    0.42
    这一切
    0.39
    सारी
    0.38
     لیګ
    0.37
    뻥
    0.37
    手册
    0.37
    эрэг
    0.36
     ይህ
    0.36
     oure
    0.36
    Activations Density 0.013%

    No Known Activations