© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51946
    Prev
    Next
    INDEX
    Explanations

    like examples of things

    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_30_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
    например
    0.33
    例えば
    0.33
     например
    0.31
     beispielsweise
    0.31
    たとえば
    0.29
     esimerkiksi
    0.28
    ೯
    0.27
     Misalnya
    0.27
     notamment
    0.27
    まさに
    0.27
    POSITIVE LOGITS
    ilerini
    0.29
     వలన
    0.29
    Financial
    0.29
    OGO
    0.29
     మీద
    0.29
     (**
    0.28
     SHA
    0.28
    ‌ನಲ್ಲಿ
    0.27
     फाइनेंशियल
    0.27
     వల్ల
    0.27
    Activations Density 0.014%

    No Known Activations