© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15333
    Prev
    Next
    INDEX
    Explanations

    parts of Java code related to class and method definitions with name and number

    oai_token-act-pair · gemini-2.0-flash

    semicolon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ma
    -0.47
    j
    -0.47
     Den
    -0.46
    yak
    -0.46
     recall
    -0.45
     den
    -0.45
    ä
    -0.45
    erial
    -0.44
    usammen
    -0.43
     ole
    -0.43
    POSITIVE LOGITS
    TagMode
    0.90
    abestanden
    0.83
     يتيمه
    0.79
    IntoConstraints
    0.74
    WriteTagHelper
    0.73
    PreferredItem
    0.70
    +#+#
    0.69
    extAlignment
    0.69
     Houſe
    0.68
    DockStyle
    0.67
    Activations Density 1.210%

    No Known Activations