© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64536
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     say
    0.38
     afternoons
    0.38
    下午
    0.38
    =`
    0.37
    say
    0.35
    }/${
    0.34
     বিকাল
    0.34
     Aircraft
    0.34
    䇝
    0.34
     Mondays
    0.33
    POSITIVE LOGITS
     mikt
    0.41
    ▣
    0.39
     ಸಮಯ
    0.39
    DU
    0.38
     বিয়ে
    0.38
     introducción
    0.38
    filters
    0.37
     चिक
    0.37
    introdu
    0.37
     etapa
    0.37
    Activations Density 0.002%

    No Known Activations