© 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. 205445
    Prev
    Next
    INDEX
    Explanations

    attention mechanism

    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
    Ireland
    0.39
     Chron
    0.38
    lineWidth
    0.38
     Ireland
    0.38
    材料
    0.38
     흰
    0.37
    saan
    0.37
     chronological
    0.37
    heast
    0.37
     transitional
    0.37
    POSITIVE LOGITS
    гля
    0.43
     looked
    0.41
     LOOK
    0.41
     look
    0.41
    粖
    0.40
    look
    0.39
    lookup
    0.39
    LOOK
    0.39
     sosp
    0.39
     য
    0.38
    Activations Density 0.005%

    No Known Activations