© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9483
    Prev
    Next
    INDEX
    Explanations

    names with the prefix "van der"

    oai_token-act-pair · gemini-2.0-flash

    der

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ImageContext
    -0.77
    بوابة
    -0.65
    imageshack
    -0.54
     Fatima
    -0.54
    tagext
    -0.53
    béco
    -0.53
    ModelSerializer
    -0.53
    homonymie
    -0.52
    atima
    -0.52
     Exile
    -0.52
    POSITIVE LOGITS
     Vande
    0.65
     Vander
    0.59
     among
    0.59
     дописавши
    0.57
    UserScript
    0.56
     Van
    0.52
    पया
    0.52
    etcode
    0.52
    ='.$
    0.52
     van
    0.51
    Activations Density 0.604%

    No Known Activations