© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14967
    Prev
    Next
    INDEX
    Explanations

    political language and political figures

    oai_token-act-pair · gemini-2.0-flash

    blog snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     itſelf
    -0.65
     crdi
    -0.63
     againſt
    -0.62
     pleaſure
    -0.62
    UseVisualStyle
    -0.60
     becauſe
    -0.58
     raiſ
    -0.58
     fubject
    -0.57
     leſs
    -0.56
     reaſon
    -0.56
    POSITIVE LOGITS
    
    0.66
     cherchés
    0.66
    RTLI
    0.57
     contradicted
    0.55
     дописавши
    0.54
    copes
    0.54
    ---|---|
    0.54
    !*\
    0.54
    cula
    0.54
     way
    0.53
    Activations Density 16.042%

    No Known Activations