© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18198
    Prev
    Next
    INDEX
    Explanations

    traffic laws and administration

    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_40_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
    bond
    0.46
    Bond
    0.44
     bond
    0.42
    bridge
    0.41
     Bridge
    0.40
    醬
    0.40
     bridge
    0.38
     bridged
    0.38
     Bridges
    0.38
     protocol
    0.38
    POSITIVE LOGITS
    Ф
    0.38
     relentless
    0.36
     инженер
    0.34
    ОВ
    0.33
     ENGINEERING
    0.33
     cristall
    0.33
     নির্ধার
    0.33
     निवेशक
    0.33
    Darwin
    0.33
    脱
    0.33
    Activations Density 0.015%

    No Known Activations