© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196570
    Prev
    Next
    INDEX
    Explanations

    send coffee

    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_27_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
     investor
    0.45
    𝐀
    0.40
     discussion
    0.39
     sedang
    0.39
     তৃণ
    0.38
     cash
    0.38
     определяет
    0.38
     stop
    0.37
     plumbing
    0.37
     warning
    0.37
    POSITIVE LOGITS
     Ahora
    0.42
    ÑO
    0.39
     direta
    0.38
    χή
    0.38
    --’
    0.38
    ไม่ใช่
    0.38
    ง่าย
    0.37
    ('');
    0.36
    作业
    0.36
    أي
    0.36
    Activations Density 0.000%

    No Known Activations