© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91225
    Prev
    Next
    INDEX
    Explanations

    blood clot / plasma / chemistry

    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
    '
    0.86
    ’
    0.62
    2
    0.59
    '")
    0.56
     Breast
    0.54
    '_{
    0.54
     Eighteenth
    0.54
    '$,
    0.54
    el
    0.53
    ड़ाई
    0.53
    POSITIVE LOGITS
     informó
    0.57
    როს
    0.57
    zcan
    0.57
    Biografia
    0.54
    мени
    0.54
    zysz
    0.53
    ઠળ
    0.52
    ന്വേഷ
    0.52
    kannya
    0.52
    ್ಟ
    0.51
    Activations Density 0.001%

    No Known Activations