© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 10289
    Prev
    Next
    INDEX
    Explanations

    Korean dates and specific events

    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
     Twice
    0.44
     lazy
    0.41
    ว้
    0.39
    US
    0.38
     couch
    0.36
     Coul
    0.36
     Couch
    0.36
    ツ
    0.35
    <0xB6>
    0.35
    ಿಯನ್
    0.35
    POSITIVE LOGITS
    Bc
    0.39
     kompleks
    0.39
     PATRIOT
    0.38
     sprawy
    0.37
     Patriot
    0.36
     uważ
    0.36
     nasled
    0.36
     संबंधों
    0.36
    ősz
    0.36
     കമ
    0.36
    Activations Density 0.030%

    No Known Activations