© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17692
    Prev
    Next
    INDEX
    Explanations

    natural disaster catastrophe tragedy

    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
    印
    0.38
     Acquisitions
    0.37
     이하
    0.37
     pick
    0.36
    Ю
    0.36
     ყ
    0.35
    ϙ
    0.35
    清
    0.34
    invalid
    0.34
     PSL
    0.34
    POSITIVE LOGITS
     disaster
    1.32
     catastrophe
    1.31
     tragedy
    1.20
     catastrophes
    1.13
     disasters
    1.05
     Disaster
    1.05
     calamity
    1.05
     tragedia
    1.02
     катастро
    1.02
    灾
    1.02
    Activations Density 0.093%

    No Known Activations