© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 203411
    Prev
    Next
    INDEX
    Explanations

    immortal, immersion, immense

    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_37_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
     recombinant
    0.38
    пии
    0.38
    八
    0.38
    ເພ
    0.37
     حال
    0.37
     next
    0.36
    Lud
    0.36
    apest
    0.36
    MathML
    0.35
    Worst
    0.35
    POSITIVE LOGITS
     الوطنية
    0.41
    떻
    0.37
    bers
    0.37
     तेव्हा
    0.37
     रीडिंग
    0.37
     gegründet
    0.37
    idlertid
    0.35
    ubuk
    0.35
     unve
    0.35
     تز
    0.35
    Activations Density 0.002%

    No Known Activations