© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27255
    Prev
    Next
    INDEX
    Explanations

    carbon pricing emissions agreements

    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_10_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
     σας
    0.31
    jie
    0.31
     Mitarbeit
    0.31
    cella
    0.30
    jä
    0.29
    jha
    0.29
    ”-
    0.29
    ,​
    0.29
    ”
    0.29
     ভাগে
    0.28
    POSITIVE LOGITS
    0.34
    ло
    0.29
    n
    0.29
    清
    0.29
    F
    0.28
     энергии
    0.28
    U
    0.28
    H
    0.28
    <0xB7>
    0.28
    لاف
    0.27
    Activations Density 0.021%

    No Known Activations