© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197778
    Prev
    Next
    INDEX
    Explanations

    submarines and navy

    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
    Con
    0.43
    拉
    0.42
     Con
    0.41
     Emmett
    0.40
    elä
    0.37
    तेरे
    0.36
    ELA
    0.36
     Coates
    0.35
    ളാ
    0.35
    Romeo
    0.35
    POSITIVE LOGITS
     بيد
    0.41
     जागरण
    0.40
     Джей
    0.40
    霁
    0.40
     Torque
    0.39
     Ja
    0.37
     ajo
    0.37
     transduction
    0.37
    烔
    0.37
    Gren
    0.37
    Activations Density 0.000%

    No Known Activations