© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6309
    Prev
    Next
    INDEX
    Explanations

    avoiding interruptions

    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
     серпня
    0.36
    tmpobj
    0.36
     देऊ
    0.35
     Dalton
    0.35
    AssetDiscovery
    0.35
    路由器
    0.35
    侓
    0.34
    㭐
    0.34
     চাল
    0.34
    ્લા
    0.33
    POSITIVE LOGITS
     interrupt
    2.78
     interruption
    2.72
     interrupted
    2.67
     Interrupt
    2.66
     interruptions
    2.63
     interrupts
    2.61
     interrupting
    2.59
    interrupt
    2.58
    Interrupt
    2.53
     interrump
    2.47
    Activations Density 0.163%

    No Known Activations