© 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
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43883
    Prev
    Next
    INDEX
    Explanations

    ethically sourced, urban, manifestation, consideration, pleasing, implementation, intimacy, treatment, lesson

    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_3_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
    is
    1.20
    지
    0.80
    يد
    0.78
    기
    0.77
    وي
    0.75
    的
    0.75
    да
    0.73
    та
    0.73
    ون
    0.73
    ش
    0.72
    POSITIVE LOGITS
    .
    0.75
    お金
    0.63
     on
    0.61
    ร่วม
    0.61
    ส
    0.59
    その
    0.59
    この
    0.58
    お知らせ
    0.57
     riguarda
    0.55
     ווא
    0.55
    Activations Density 0.112%

    No Known Activations