© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215854
    Prev
    Next
    INDEX
    Explanations

    divorce and marriage rates

    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
    ITwitter
    0.45
    Abraham
    0.40
     household
    0.39
     radiator
    0.39
    居家
    0.38
    阆
    0.38
     relacionamento
    0.37
    Ⓐ
    0.37
    Emer
    0.37
    household
    0.37
    POSITIVE LOGITS
    harma
    0.47
    цвет
    0.40
     온도
    0.36
    引入
    0.36
    ੍
    0.36
    色
    0.35
    식회사
    0.35
     расчет
    0.35
     courants
    0.35
     цвет
    0.34
    Activations Density 0.002%

    No Known Activations