© 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. 4171
    Prev
    Next
    INDEX
    Explanations

    terms and symbols related to programming, legal language, and research/scientific concepts.

    oai_token-act-pair · gemini-2.0-flash

    Technical language

    np_max-act · 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
     itſelf
    -0.82
     firebaseConfig
    -0.70
     NDEBUG
    -0.65
     تضيفلها
    -0.65
     tartalomajánló
    -0.63
    tagHelperRunner
    -0.63
     Mahabhar
    -0.63
    protoimpl
    -0.59
     ſche
    -0.59
     Dues
    -0.58
    POSITIVE LOGITS
    ChildScrollView
    0.52
    RegressionTest
    0.48
     denk
    0.47
    Tazama
    0.47
     municipios
    0.47
     precedentes
    0.45
    StoreMessageInfo
    0.45
    entretien
    0.44
     the
    0.44
    quelize
    0.43
    Activations Density 7.142%

    No Known Activations