© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29419
    Prev
    Next
    INDEX
    Explanations

    undercutting and undermining

    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
     જય
    0.40
     ادا
    0.38
    枳
    0.37
    箒
    0.36
    崤
    0.36
    यु
    0.35
     Deux
    0.35
    лек
    0.35
    俣
    0.35
     spiritual
    0.34
    POSITIVE LOGITS
     undercut
    1.86
     unders
    1.34
     undermining
    1.13
     Und
    1.09
    unders
    1.08
     undermined
    1.06
     undermine
    1.05
     undermines
    1.03
    Und
    1.02
     अंडर
    0.84
    Activations Density 0.091%

    No Known Activations