© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4103
    Prev
    Next
    INDEX
    Explanations

    exploit, abuse, or endanger

    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
     бизне
    0.42
    🕴
    0.37
    ",[(
    0.36
    үкт
    0.36
    pect
    0.35
    蟳
    0.35
     Рей
    0.35
     किफायती
    0.34
    <unused55>
    0.33
     businesses
    0.33
    POSITIVE LOGITS
     longterm
    0.48
     long
    0.44
    长期
    0.43
    長期
    0.42
    ึ
    0.42
    ധാ
    0.41
     λειτουργ
    0.40
    מות
    0.39
    长时间
    0.37
     meteor
    0.37
    Activations Density 0.061%

    No Known Activations