© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6418
    Prev
    Next
    INDEX
    Explanations

    law and response related boilerplate.

    oai_token-act-pair · gemini-2.0-flash

    quotations and legal passages

    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
    <bos>
    -0.77
     виправивши
    -0.75
    ImageContext
    -0.62
     Sku
    -0.61
     дописавши
    -0.61
    IUrlHelper
    -0.60
     Torah
    -0.54
     通販
    -0.53
     marcha
    -0.53
     naïve
    -0.53
    POSITIVE LOGITS
    formik
    0.64
     normaux
    0.60
     financières
    0.57
     présidenti
    0.57
    StateException
    0.56
     démocr
    0.54
     liderazgo
    0.52
     fondament
    0.52
     fumée
    0.51
    dotte
    0.51
    Activations Density 1.265%

    No Known Activations