© 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. 208002
    Prev
    Next
    INDEX
    Explanations

    secured, seal, waterproof, polymer, latex

    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
    阿里巴巴
    0.40
    hanging
    0.39
    khidmat
    0.38
    釭
    0.38
    ്യമ
    0.38
     ማድረግ
    0.38
    锤
    0.37
    餐厅
    0.37
     መጠቀም
    0.36
    ematic
    0.35
    POSITIVE LOGITS
     Waterproof
    0.45
     Polymer
    0.45
     Torr
    0.40
     Bloem
    0.39
     Renewable
    0.39
     Latex
    0.39
     polymer
    0.39
     Šk
    0.38
     TLR
    0.38
     waterproof
    0.38
    Activations Density 0.019%

    No Known Activations