© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 203266
    Prev
    Next
    INDEX
    Explanations

    overwhelming

    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_46_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
    烽
    0.40
    试
    0.40
    惮
    0.39
     Dunn
    0.39
    ✔
    0.37
     Diario
    0.37
    ८
    0.36
     দৈর্ঘ
    0.35
    ᚗ
    0.35
    SUS
    0.34
    POSITIVE LOGITS
     overw
    1.05
     überw
    0.97
    OVER
    0.80
     overwhelmingly
    0.80
     overwrite
    0.79
    オーバー
    0.78
     overwhelming
    0.77
     overwhelmed
    0.77
     whe
    0.77
     overpower
    0.76
    Activations Density 0.005%

    No Known Activations