© 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. 223679
    Prev
    Next
    INDEX
    Explanations

    stroll along, over, through

    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
    a
    0.57
    น
    0.57
    ל
    0.55
    นอก
    0.52
    n
    0.49
    ה
    0.46
    न
    0.45
    н
    0.45
    x
    0.44
     rewritten
    0.44
    POSITIVE LOGITS
    ging
    0.57
    时间
    0.55
    𝐆
    0.53
    بية
    0.51
    рты
    0.49
    餐厅
    0.48
    az
    0.47
    .。
    0.47
    做
    0.47
    𝐠
    0.47
    Activations Density 0.002%

    No Known Activations