© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4765
    Prev
    Next
    INDEX
    Explanations

    words or symbols commonly used in scientific publications, in math, physics, chemistry, biology, and/or medicine, and also finds gourmet food preparation

    oai_token-act-pair · gemini-2.0-flash

    reg

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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>
    -0.57
    ’
    -0.50
     gospel
    -0.46
    Hochspringen
    -0.46
    formik
    -0.44
    thoff
    -0.43
    empuan
    -0.42
    phan
    -0.42
     genome
    -0.40
    rao
    -0.40
    POSITIVE LOGITS
    Datuak
    1.05
    Portail
    0.82
    featureID
    0.81
     propOrder
    0.79
    BeginContext
    0.78
    MigrationBuilder
    0.74
    TagMode
    0.70
    AddTagHelper
    0.68
    tagHelperRunner
    0.65
    Portale
    0.65
    Activations Density 9.307%

    No Known Activations