© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2117
    Prev
    Next
    INDEX
    Explanations

    code blocks, documentation, API descriptions, and parameters in code or documentation.

    oai_token-act-pair · gemini-2.0-flash

    coding lists

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    rxjs
    -0.50
    CppMethod
    -0.43
     MenuView
    -0.40
    successfully
    -0.39
    ScopeManager
    -0.39
     EconPapers
    -0.39
    WEBPACK
    -0.38
    tonsoft
    -0.38
    
    -0.37
     pulumi
    -0.36
    POSITIVE LOGITS
    PyExc
    0.74
    ExecuteReader
    0.72
    ⓧ
    0.68
     defaultstate
    0.66
     exposing
    0.65
     passing
    0.63
     returning
    0.62
    orgon
    0.62
     where
    0.60
     filling
    0.59
    Activations Density 6.762%

    No Known Activations