© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12519
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially sections of code dealing with conditionals, assignment, or object properties.

    oai_token-act-pair · gemini-2.0-flash

    coding symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    DockStyle
    -1.36
     autorytatywna
    -1.25
     كومونز
    -1.20
    MigrationBuilder
    -1.16
    AccessorTable
    -1.14
    awtextra
    -1.10
     EconPapers
    -1.10
    AnchorStyles
    -1.06
     kasarigan
    -1.03
     disambiguazione
    -1.03
    POSITIVE LOGITS
     
    0.73
    4
    0.63
    ↵↵
    0.58
    2
    0.58
    5
    0.57
    -
    0.57
    ,
    0.56
    6
    0.56
     to
    0.56
    0
    0.54
    Activations Density 9.907%

    No Known Activations