© 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-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13011
    Prev
    Next
    INDEX
    Explanations

    the state name "New Jersey"

    oai_token-act-pair · gemini-2.0-flash

    Jersey

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NY
    -0.76
     Brooklyn
    -0.68
     NYC
    -0.60
     London
    -0.58
     Paris
    -0.57
     ny
    -0.56
     Chicago
    -0.56
    isele
    -0.55
    NY
    -0.55
    ニューヨーク
    -0.54
    POSITIVE LOGITS
    RenderAtEndOf
    1.07
     betweenstory
    0.94
     auroit
    0.92
    expandindo
    0.90
     "..\..\..\
    0.90
     "..\..\
    0.89
     étoit
    0.88
    NameInMap
    0.87
    MessageTagHelper
    0.86
     feroit
    0.82
    Activations Density 0.252%

    No Known Activations