© 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
    2. Gemma-3-4B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9435
    Prev
    Next
    INDEX
    Explanations

    pharmacy drugs

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     määr
    0.67
     flexibles
    0.65
     sedentary
    0.65
    reathe
    0.64
     parenchyma
    0.63
    ˟
    0.60
     बचाव
    0.60
    衫
    0.60
     ছেড়ে
    0.60
     transportasi
    0.60
    POSITIVE LOGITS
     drug
    1.31
     Drug
    1.26
    pharmac
    1.19
    Drug
    1.18
     pharmacy
    1.17
     Pharmacy
    1.16
     Pharmac
    1.14
     pharm
    1.12
     pharmacist
    1.09
     pharmaceut
    1.09
    Activations Density 0.105%

    No Known Activations