© 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. 4093
    Prev
    Next
    INDEX
    Explanations

    language about defining or naming something

    oai_token-act-pair · gemini-2.0-flash

    Naming or considering

    np_max-act · gemini-2.0-flash

    naming verbs

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     <<<<<<<<<<<<<<
    -0.75
    SpringBootTest
    -0.75
     CreateTagHelper
    -0.73
    ViewImports
    -0.64
    Personendaten
    -0.63
     autorytatywna
    -0.63
     kaarangay
    -0.63
    MemoryWarning
    -0.63
     EnglishChoose
    -0.62
    iprot
    -0.62
    POSITIVE LOGITS
     MainAxisSize
    0.56
    verwijspagina
    0.49
    DAOImpl
    0.45
    isClosed
    0.44
    raborty
    0.43
    ImageField
    0.42
    DateFormat
    0.41
     AssemblyProduct
    0.41
    ները
    0.40
    DaoImpl
    0.40
    Activations Density 0.356%

    No Known Activations