© 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-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7361
    Prev
    Next
    INDEX
    Explanations

    mentions of events being held or taking place, along with associated dates and locations

    oai_token-act-pair · gemini-2.0-flash

    Events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    writeField
    -0.46
     været
    -0.42
     espèces
    -0.39
    where
    -0.39
     generated
    -0.39
     recettes
    -0.38
    ɚ
    -0.37
    VS
    -0.36
    äldrar
    -0.36
     Obwohl
    -0.36
    POSITIVE LOGITS
    +:+
    0.86
     Савезне
    0.83
    RenderAtEndOf
    0.78
    expandindo
    0.74
    adpleegd
    0.71
    PerformLayout
    0.70
     يتيمه
    0.70
     >=",
    0.69
    
    0.69
     calendriers
    0.67
    Activations Density 0.936%

    No Known Activations