© 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. 207678
    Prev
    Next
    INDEX
    Explanations

    convenience

    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
    ADOC
    0.18
    igenes
    0.18
     família
    0.18
    WAYS
    0.18
     interesar
    0.18
    逹
    0.18
    alada
    0.17
    年
    0.17
    тельного
    0.17
    生活中
    0.17
    POSITIVE LOGITS
     kefir
    0.21
     көзге
    0.20
     robust
    0.19
     Type
    0.19
     burrito
    0.19
     temporary
    0.19
     shampoo
    0.19
     template
    0.19
     grinder
    0.18
    Тем
    0.18
    Activations Density 0.002%

    No Known Activations