© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 699
    Prev
    Next
    INDEX
    Explanations

    line breaks

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    WaitGroup
    -0.65
     OnInit
    -0.60
    serviceWorker
    -0.59
    migrationBuilder
    -0.50
    GEBURTSDATUM
    -0.50
    FormsModule
    -0.49
     BrowserModule
    -0.48
    Portail
    -0.47
    InstanceState
    -0.47
    BuilderFactory
    -0.46
    POSITIVE LOGITS
    AsUp
    0.66
    ViewFeatures
    0.65
    SharedDtor
    0.63
    Jîn
    0.61
    enumi
    0.60
    couverte
    0.60
    SerializedSize
    0.59
     Савезне
    0.59
    цездатний
    0.59
    kloped
    0.57
    Activations Density 2.230%

    No Known Activations