© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 212562
    Prev
    Next
    INDEX
    Explanations

    bomb disposal

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_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
    xcschemes
    0.39
     oregano
    0.39
     ').
    0.39
    畸
    0.39
    ydro
    0.38
    .');
    0.37
     jobSearch
    0.36
    gatsby
    0.35
    }^{-}
    0.35
    дыду
    0.34
    POSITIVE LOGITS
     Sapp
    1.00
     sa
    0.86
    sapp
    0.82
    Sapp
    0.80
     bomb
    0.77
     sapp
    0.76
     Bomb
    0.74
     disposal
    0.73
     Engineers
    0.72
     са
    0.71
    Activations Density 0.001%

    No Known Activations