© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 434
    Prev
    Next
    INDEX
    Explanations

    code related to comparing data types in C++ or similar languages

    oai_token-act-pair · gemini-2.0-flash

    say [code]

    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
    ± 
    -0.75
     propOrder
    -0.73
    ública
    -0.71
    !*\
    -0.71
    eryllium
    -0.69
    onets
    -0.68
    ATIVO
    -0.68
    }}]{
    -0.68
    gebn
    -0.68
    ricts
    -0.68
    POSITIVE LOGITS
    "
    0.34
     habet
    0.30
     maniere
    0.29
    “
    0.28
     haine
    0.28
     bluse
    0.28
     eorum
    0.27
    format
    0.26
    info
    0.26
    input
    0.25
    Activations Density 3.757%

    No Known Activations