© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242834
    Prev
    Next
    INDEX
    Explanations

    window settings or system files

    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_40_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
    ມ
    0.43
    Module
    0.41
     WH
    0.40
    模块
    0.39
    这一点
    0.39
    module
    0.38
    Gravity
    0.38
     maneuvering
    0.38
    解锁
    0.38
     boxed
    0.37
    POSITIVE LOGITS
    WIN
    0.39
     threat
    0.38
    Android
    0.38
    숙
    0.37
     승
    0.36
    経営
    0.36
     경영
    0.36
     ഇട
    0.36
    ledi
    0.36
    団
    0.35
    Activations Density 0.038%

    No Known Activations