© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 239615
    Prev
    Next
    INDEX
    Explanations

    nausea, vomiting

    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_25_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
    ((-
    0.37
     lips
    0.37
     year
    0.35
     ability
    0.34
     lipid
    0.34
     prêts
    0.34
     credit
    0.34
     Spence
    0.34
     étages
    0.34
     produit
    0.33
    POSITIVE LOGITS
     হরি
    0.49
    ﷲ
    0.45
    вайтесь
    0.44
    ัญหา
    0.43
     worrying
    0.42
    寵
    0.41
     সেনাবাহ
    0.41
    黴
    0.41
    aniyati
    0.40
    ﾔ
    0.40
    Activations Density 0.001%

    No Known Activations