© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42940
    Prev
    Next
    INDEX
    Explanations

    pertuzumab, trastuzumab

    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_3_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
    ↵↵
    0.71
     croire
    0.71
    고
    0.59
    қты
    0.57
    、『
    0.56
    is
    0.55
    сь
    0.55
    д
    0.54
    ີ້
    0.53
     influencia
    0.52
    POSITIVE LOGITS
    ОР
    0.82
     I
    0.71
     socialist
    0.70
    ă
    0.64
     Socialist
    0.64
    í
    0.62
     d
    0.62
    o
    0.61
    ü
    0.60
    :
    0.59
    Activations Density 0.002%

    No Known Activations