© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204602
    Prev
    Next
    INDEX
    Explanations

    mermaid code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     diagram
    2.56
    Diagram
    2.38
    diagram
    2.36
     Diagram
    2.33
     diagrams
    2.23
     Diagrams
    2.06
     diagrama
    2.02
    図
    1.54
    图
    1.47
     schematic
    1.41
    POSITIVE LOGITS
    ٹس
    0.40
     प्रतिष्ठ
    0.40
     Nationalist
    0.37
     Arthur
    0.36
     Republican
    0.36
     Hed
    0.35
     legion
    0.34
     практики
    0.34
     Mar
    0.34
     Legion
    0.34
    Activations Density 0.001%

    No Known Activations