© 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. 2835
    Prev
    Next
    INDEX
    Explanations

    code-related snippets, particularly Java and SQL

    oai_token-act-pair · gemini-2.0-flash

    Special characters/foreign words

    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
    ptonshire
    -0.68
    ReusableCell
    -0.65
    illable
    -0.60
    מבר
    -0.59
     diana
    -0.59
    ganu
    -0.56
    ppur
    -0.55
    ccini
    -0.55
    timewa
    -0.55
    ấm
    -0.55
    POSITIVE LOGITS
    //
    0.48
    #
    0.47
     Riproduzione
    0.45
     gider
    0.44
    «
    0.44
     automatiques
    0.43
    <!--
    0.42
     étrangères
    0.41
    ‘‘
    0.41
    //!
    0.41
    Activations Density 12.660%

    No Known Activations