© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163857
    Prev
    Next
    INDEX
    Explanations

    US Presidential election, Trump walked, civil unrest, data privacy, Facebook announced, LA Dodgers won, chess rey

    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_31_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
    Remote
    0.40
    system
    0.37
    Wide
    0.37
    自己
    0.35
    体重
    0.35
    atsuki
    0.35
    薙
    0.35
    anci
    0.34
    zeigen
    0.34
    Ninja
    0.33
    POSITIVE LOGITS
     Corp
    0.38
     ति
    0.36
    ]=-
    0.36
     Vodka
    0.35
     extinguish
    0.35
     perfume
    0.34
     blond
    0.34
    markUp
    0.34
     parche
    0.34
     incênd
    0.33
    Activations Density 0.000%

    No Known Activations