© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5517
    Prev
    Next
    INDEX
    Explanations

    mathematical equations related to physics, data science, and abstract concepts.

    oai_token-act-pair · gemini-2.0-flash

    dividing into groups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     opleiding
    -0.57
    SBATCH
    -0.54
    emlrt
    -0.54
    kosh
    -0.53
     oposición
    -0.52
    jeune
    -0.52
     educativos
    -0.52
     formazione
    -0.52
     ambientales
    -0.52
     humains
    -0.51
    POSITIVE LOGITS
    featureID
    0.68
     AttributeSet
    0.64
     Савезне
    0.60
     Pristupljeno
    0.60
    jsxFileName
    0.58
     समीक्षाओं
    0.57
    aktery
    0.57
    FieldBuilder
    0.57
     shouldBe
    0.56
    TestingModule
    0.55
    Activations Density 4.793%

    No Known Activations