© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15667
    Prev
    Next
    INDEX
    Explanations

    Physiology or Medicine awards

    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_15_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
    ere
    0.61
    are
    0.56
    aye
    0.56
    il
    0.55
    ari
    0.55
    zea
    0.55
    ẖ
    0.54
    arle
    0.53
    enc
    0.52
    ară
    0.52
    POSITIVE LOGITS
     surgeon
    0.59
    医生
    0.59
     neuropathy
    0.59
    監
    0.55
     hemodynamic
    0.55
     nonexpansive
    0.54
     Pulitzer
    0.54
     doctor
    0.53
     physician
    0.53
     Surgeon
    0.53
    Activations Density 0.002%

    No Known Activations