© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9797
    Prev
    Next
    INDEX
    Explanations

    measurements or proportions

    oai_token-act-pair · gemini-2.0-flash

    fractions and percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    rrggbb
    -0.77
     sulfon
    -0.62
    abestanden
    -0.59
    abstractmethod
    -0.59
    modb
    -0.57
    codegen
    -0.57
    makeConstraints
    -0.57
    roek
    -0.56
    createCanvas
    -0.56
    HEP
    -0.56
    POSITIVE LOGITS
    SharedDtor
    0.65
     AssemblyCompany
    0.60
    ⓧ
    0.59
    numerusform
    0.59
    InputTagHelper
    0.57
    SharedCtor
    0.54
     unknownFields
    0.49
     mergeFrom
    0.48
     provincie
    0.45
    EndGlobalSection
    0.45
    Activations Density 1.103%

    No Known Activations