© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206244
    Prev
    Next
    INDEX
    Explanations

    somewhere between, lies in, frequencies below, Blockchain is, falls within

    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_37_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
     bridge
    1.99
     bridging
    1.82
     Bridge
    1.70
    Bridge
    1.69
     bridges
    1.60
    bridge
    1.59
    桥
    1.59
     bridged
    1.59
     BRIDGE
    1.47
    橋
    1.47
    POSITIVE LOGITS
     paired
    0.36
     বাহাদুর
    0.36
    ceptar
    0.35
     subunits
    0.34
    appar
    0.34
    пель
    0.34
     subtypes
    0.33
    nder
    0.33
     Kxc
    0.33
     ядра
    0.32
    Activations Density 0.038%

    No Known Activations