© 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. 232919
    Prev
    Next
    INDEX
    Explanations

    poverty

    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
    Berlin
    0.40
    -(-
    0.40
     гидро
    0.39
    靖
    0.36
     dot
    0.35
    स्य
    0.35
     ಶು
    0.35
     Prestige
    0.35
    澥
    0.35
     הג
    0.34
    POSITIVE LOGITS
    貧
    2.34
     poverty
    2.30
    贫
    2.25
     impoverished
    2.23
     Poverty
    2.16
     pobreza
    2.05
     impover
    1.91
     pobres
    1.91
     pover
    1.91
     poor
    1.85
    Activations Density 0.058%

    No Known Activations