© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31672
    Prev
    Next
    INDEX
    Explanations

    say Bridge

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    тивная
    0.41
     Tactics
    0.38
     anex
    0.38
    лән
    0.38
    铯
    0.37
     tactics
    0.35
     Versuch
    0.35
    емая
    0.34
     consec
    0.34
    圭
    0.34
    POSITIVE LOGITS
     bridge
    3.38
     Bridge
    3.11
    Bridge
    3.06
     bridges
    2.95
    bridge
    2.94
     BRIDGE
    2.84
    桥
    2.83
    橋
    2.73
     bridging
    2.69
    BRIDGE
    2.64
    Activations Density 0.004%

    No Known Activations