© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4773
    Prev
    Next
    INDEX
    Explanations

    war, Germany, measure

    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_39_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
     Baghdad
    0.43
    pellier
    0.41
     Afghan
    0.41
    𝙴
    0.40
    Afghanistan
    0.40
     Naval
    0.39
     عراق
    0.39
    蹊
    0.39
     ወደ
    0.39
     noreferrer
    0.39
    POSITIVE LOGITS
     mobile
    0.38
    SD
    0.38
     Datensch
    0.38
     Handels
    0.37
    cap
    0.37
    Mobile
    0.36
    Capp
    0.36
    altra
    0.35
    努
    0.34
    obile
    0.34
    Activations Density 0.027%

    No Known Activations