© 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. 9232
    Prev
    Next
    INDEX
    Explanations

    code syntax, specifically related to java or similar languages

    oai_token-act-pair · gemini-2.0-flash

    < or (

    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
    begingroup
    -0.35
    gemeester
    -0.32
    potranspiration
    -0.32
    unsqueeze
    -0.31
     burbuja
    -0.29
    eins
    -0.28
    Démographie
    -0.27
    ysty
    -0.26
    })));
    -0.26
    ejercicio
    -0.26
    POSITIVE LOGITS
     assassination
    0.69
     assassinated
    0.67
     raiſ
    0.64
     subspecies
    0.64
     uſed
    0.62
     virginity
    0.62
     psychoanalysis
    0.61
     Mejía
    0.61
     preſent
    0.59
     adjournment
    0.59
    Activations Density 12.503%

    No Known Activations