© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9903
    Prev
    Next
    INDEX
    Explanations

    message content

    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
     பாத
    0.32
     systém
    0.32
    banners
    0.32
    咉
    0.31
     विडियो
    0.30
    システム
    0.29
     बनकर
    0.29
    าง
    0.28
    ⊰
    0.28
     военной
    0.28
    POSITIVE LOGITS
     Ingersoll
    0.30
    ínt
    0.29
    ONEDB
    0.29
    plicit
    0.27
    मील
    0.26
     Db
    0.26
    蠵
    0.26
    log
    0.26
    ức
    0.26
    ingi
    0.26
    Activations Density 0.001%

    No Known Activations