© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3253
    Prev
    Next
    INDEX
    Explanations

    graph nodes and edges

    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_39_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
     engagement
    0.41
    加速度
    0.37
     integrale
    0.37
     localización
    0.36
    墾
    0.36
    engagement
    0.35
    occupied
    0.35
     palace
    0.35
    絽
    0.35
     previsão
    0.34
    POSITIVE LOGITS
     nodes
    1.01
     vertex
    0.96
     Nodes
    0.96
     node
    0.96
     edges
    0.94
     Node
    0.93
    nodes
    0.93
     vertices
    0.90
    节点
    0.89
    Edges
    0.88
    Activations Density 0.172%

    No Known Activations