© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2357
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and names, particularly of methods and types

    oai_token-act-pair · gemini-2.0-flash

    programming data structure size/count

    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
    contentLoaded
    -0.93
     فريبيس
    -0.81
    Хьажоргаш
    -0.75
     Normdatei
    -0.75
     tartalomajánló
    -0.73
    GEBURTSDATUM
    -0.71
     OFDb
    -0.70
     Cæsar
    -0.66
    tagext
    -0.65
    XmlEnum
    -0.65
    POSITIVE LOGITS
    newArrayList
    0.71
    ArrayList
    0.52
     popular
    0.50
    WaitGroup
    0.49
    DataSetChanged
    0.48
    AnchorStyles
    0.47
    seguida
    0.47
    Interesting
    0.45
    append
    0.45
    NSMutable
    0.44
    Activations Density 2.831%

    No Known Activations