© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 99322
    Prev
    Next
    INDEX
    Explanations

    hospital, history, length, department

    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_14_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
     mood
    0.51
    睄
    0.51
    嚗
    0.47
     tonal
    0.46
     probabilmente
    0.46
     melalui
    0.45
     Moody
    0.45
     alue
    0.45
     getId
    0.45
     Dhoni
    0.45
    POSITIVE LOGITS
    जु
    0.54
    жен
    0.47
     режима
    0.46
    ای
    0.45
    ાસ
    0.45
    бен
    0.45
    ام
    0.44
    గ
    0.44
    icmp
    0.44
    ин
    0.43
    Activations Density 0.000%

    No Known Activations