© 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-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9686
    Prev
    Next
    INDEX
    Explanations

    disasters

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     দখল
    0.78
     দখ
    0.76
    劵
    0.68
     बराबरी
    0.68
     क्लो
    0.66
    SalesReport
    0.64
    cookies
    0.64
    菀
    0.64
    讪
    0.64
     Bucc
    0.63
    POSITIVE LOGITS
     disasters
    2.89
     disaster
    2.80
     catastrophes
    2.51
     catastrophe
    2.49
     Disaster
    2.41
     calamities
    2.17
     tragedy
    2.16
     calamity
    2.15
     tragedies
    2.11
     catastrophic
    2.01
    Activations Density 0.160%

    No Known Activations