© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 33526
    Prev
    Next
    INDEX
    Explanations

    unemployment benefits and claims

    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_31_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
    劳动
    0.38
    Ŵ
    0.36
    =="
    0.35
    重启
    0.35
     NPR
    0.35
     labor
    0.34
     कोविड
    0.34
    瓒
    0.33
     Labor
    0.33
     MyBatis
    0.33
    POSITIVE LOGITS
     collusion
    0.42
    hein
    0.39
    urricular
    0.39
    Harmony
    0.38
     harmony
    0.37
    idenav
    0.37
    спо
    0.36
     vign
    0.36
    愍
    0.36
     Haryana
    0.36
    Activations Density 0.003%

    No Known Activations