© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209950
    Prev
    Next
    INDEX
    Explanations

    coconut meat

    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_20_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
     러시아
    0.10
     CLEAN
    0.09
     chó
    0.09
     burrito
    0.09
     اﻷ
    0.09
     parámetro
    0.09
     Warszawie
    0.09
    ⱼ
    0.09
    状況
    0.09
    igui
    0.09
    POSITIVE LOGITS
    年纪
    0.10
     आइये
    0.09
    finders
    0.09
    revalidator
    0.09
     tentu
    0.09
    പ്പെടുന്ന
    0.09
     ঊর্ধ্ব
    0.08
    Commands
    0.08
     Proposal
    0.08
     Campaigns
    0.08
    Activations Density 0.002%

    No Known Activations