© 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. 3940
    Prev
    Next
    INDEX
    Explanations

    academic publications and data repositories related to machine learning

    oai_token-act-pair · gemini-2.0-flash

    academic publications on AI

    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
    memoized
    -0.68
     GenerationType
    -0.62
    bitField
    -0.62
    SharedDtor
    -0.60
    QRST
    -0.60
    TagHelpers
    -0.59
    CloseOperation
    -0.59
    dbo
    -0.58
    osex
    -0.57
    IsPostBack
    -0.57
    POSITIVE LOGITS
     industriels
    0.42
     économie
    0.42
    clickOn
    0.39
    vedať
    0.38
     venons
    0.38
     DELLE
    0.38
     Técnicas
    0.37
     Knowledge
    0.37
     circuits
    0.36
     fuite
    0.36
    Activations Density 3.510%

    No Known Activations