© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 51180
    Prev
    Next
    INDEX
    Explanations

    months have passed since his last upload, and concerningly, there is currently no publicly available information regarding his well-being, leaving his audience worried and*(Source: *The Register*, "EU AI Act is a 'regulatory mess' say software industry bodies," Feb 2024: [https://www.theregister.com/2024/02*(... Feb 2024: [https://www.theregister.com/2024/02/25/eu_ai_act_regulatory_mess_say_software_industry_bodies/](https://www.theregister.com/2024/02/25/eu_ai_act_regulatory_mess_say_software_industry_bodies/)*(May 2020 by @favordavid.dates and time ranges

    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_31_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
     jumping
    0.44
    uhnya
    0.39
    ώς
    0.39
    while
    0.38
     mientras
    0.38
    ానం
    0.37
     while
    0.36
     While
    0.36
    সিডেন্ট
    0.35
    MLS
    0.35
    POSITIVE LOGITS
     GB
    0.44
     कार्बो
    0.37
    gb
    0.35
     গত
    0.35
    USERNAME
    0.35
     органі
    0.35
    有機
    0.35
    ប្រតិ
    0.34
     DateTime
    0.34
    oron
    0.34
    Activations Density 0.061%

    No Known Activations