© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6066
    Prev
    Next
    INDEX
    Explanations

    physical demands or sedentary lifestyle

    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_40_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
     취
    0.36
    ユーザー
    0.35
    溶解
    0.35
    Solve
    0.35
    ällen
    0.35
    Justice
    0.35
     হ
    0.34
    위
    0.34
    ရှ
    0.34
     Detective
    0.34
    POSITIVE LOGITS
     coworker
    0.44
    ectors
    0.43
     поба
    0.41
    fato
    0.41
    vention
    0.40
     tala
    0.39
    ピオン
    0.39
    𝖔
    0.39
     coworkers
    0.38
     flanges
    0.38
    Activations Density 0.001%

    No Known Activations