© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92856
    Prev
    Next
    INDEX
    Explanations

    traffic light timing and signals

    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_11_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
     İn
    0.60
    ά
    0.60
    ی
    0.58
     clipart
    0.55
     receber
    0.54
     án
    0.53
     recebeu
    0.53
    ים
    0.51
     vă
    0.51
     envío
    0.51
    POSITIVE LOGITS
    šnje
    0.55
    RIG
    0.51
     Geschichten
    0.50
    Rig
    0.50
    ="...">
    0.50
    otest
    0.50
    ปี
    0.47
     Tahun
    0.47
    意見
    0.46
    urra
    0.46
    Activations Density 0.010%

    No Known Activations