© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10183
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and terminology

    oai_token-act-pair · gemini-2.0-flash

    connectivity

    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
    kuuta
    -0.64
     iprot
    -0.63
    InputTagHelper
    -0.61
    yntaxException
    -0.55
    signol
    -0.55
     Physik
    -0.54
    minecraftforge
    -0.54
    obiology
    -0.54
    וכ
    -0.54
    AUX
    -0.52
    POSITIVE LOGITS
     PhpStorm
    0.73
    Datuak
    0.73
    SourceChecksum
    0.71
    styleType
    0.70
     AssemblyVersion
    0.69
    Portail
    0.68
     nemici
    0.65
     fermés
    0.65
    fontawesome
    0.65
     سكانية
    0.65
    Activations Density 4.625%

    No Known Activations