© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 209644
    Prev
    Next
    INDEX
    Explanations

    sensitivities and allergies

    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_19_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
    тья
    0.31
    </b>
    0.30
    мага
    0.30
    ǔ
    0.30
     ☆
    0.29
    зина
    0.29
     ہوں۔
    0.29
     upang
    0.29
    تبه
    0.29
     пункта
    0.29
    POSITIVE LOGITS
    家庭
    0.36
     সংযোগ
    0.31
     കുടുംബ
    0.31
    LAS
    0.31
    las
    0.30
    যাত্রা
    0.29
     রোগী
    0.29
    Las
    0.28
    如今
    0.28
    壓
    0.28
    Activations Density 0.026%

    No Known Activations