© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16924
    Prev
    Next
    INDEX
    Explanations

    telegram, PORT, faq, computing

    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
     Suns
    0.42
    ronome
    0.38
    ಪ್ರ
    0.38
    പ്ര
    0.38
    RIX
    0.37
     انقلاب
    0.37
    듀
    0.37
    columnwidth
    0.36
    ObjectIndex
    0.36
    قدم
    0.35
    POSITIVE LOGITS
     telegraph
    0.47
     Telegraph
    0.46
     telegram
    0.37
    querque
    0.36
     টেলিগ্রাফ
    0.36
     muddy
    0.36
    iences
    0.35
     &[
    0.35
    苦
    0.35
    ває
    0.35
    Activations Density 0.009%

    No Known Activations