© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 178203
    Prev
    Next
    INDEX
    Explanations

    Threading, on Day

    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_24_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
    indexPath
    0.30
     orchestr
    0.29
     arrêt
    0.29
    岛
    0.27
     brokers
    0.27
     precisely
    0.27
     blade
    0.27
    PIPE
    0.27
    Schmidt
    0.27
    particles
    0.26
    POSITIVE LOGITS
    記入
    0.32
     জিনি
    0.31
     LaSalle
    0.30
    不够
    0.30
    䨘
    0.30
    秙
    0.29
     Guar
    0.29
    䄸
    0.29
     daim
    0.29
     використову
    0.29
    Activations Density 0.000%

    No Known Activations