© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198819
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     nâng
    0.42
     Nutr
    0.40
     Corpus
    0.39
     Unterschied
    0.39
     நூற்ற
    0.39
     Buy
    0.38
    檳
    0.38
     Multicolor
    0.38
     intersected
    0.38
     Seal
    0.38
    POSITIVE LOGITS
    @[
    0.38
    stdlib
    0.37
    [:
    0.37
    嵃
    0.36
    [:]
    0.36
    ংস
    0.36
    只有
    0.35
    iform
    0.35
    HIB
    0.34
    Magento
    0.34
    Activations Density 0.003%

    No Known Activations