© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 157412
    Prev
    Next
    INDEX
    Explanations

    Alpaca model

    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_50_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
     P
    0.46
    nhof
    0.44
    gal
    0.43
    GAL
    0.42
    ifan
    0.41
     ११
    0.41
     १०
    0.41
    nega
    0.41
    mann
    0.40
    콥
    0.40
    POSITIVE LOGITS
     SOI
    0.41
     Redwood
    0.38
    ⴰ
    0.38
     Giron
    0.36
     Ging
    0.36
     Sequoia
    0.36
     thermal
    0.35
     কাত
    0.35
     SO
    0.34
     reproducing
    0.34
    Activations Density 0.001%

    No Known Activations