© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16688
    Prev
    Next
    INDEX
    Explanations

    agent or broker

    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_34_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
    qz
    0.40
    救
    0.40
    섹
    0.36
    कू
    0.36
     മനു
    0.36
    जू
    0.35
    োয়া
    0.35
    髹
    0.35
    getItemId
    0.34
     keram
    0.34
    POSITIVE LOGITS
     agent
    0.94
     agents
    0.85
     Agent
    0.84
     agente
    0.83
     broker
    0.82
     Agents
    0.80
    Agent
    0.79
    agent
    0.78
     brokers
    0.78
     агент
    0.78
    Activations Density 0.024%

    No Known Activations