© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 196365
    Prev
    Next
    INDEX
    Explanations

    details

    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_9_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
     covariance
    0.56
    \,\
    0.54
     approxim
    0.46
     Descriptive
    0.45
     Heads
    0.44
    ವುದು
    0.43
    णीय
    0.43
    ۸
    0.42
    ണ്ട
    0.42
     derivations
    0.42
    POSITIVE LOGITS
    银
    0.58
    ميم
    0.56
    为什么
    0.54
    进程
    0.54
    เก
    0.52
    解决
    0.50
    𝓸
    0.47
    优化
    0.47
    难
    0.47
    拒绝
    0.46
    Activations Density 0.000%

    No Known Activations