© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 707
    Prev
    Next
    INDEX
    Explanations

    code related keywords, such as CLASS, INT, and HTTP

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash

    _

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     NDEBUG
    -0.46
    expandindo
    -0.41
    LookAnd
    -0.41
    ArgsConstructor
    -0.41
     RISERV
    -0.40
    sizeCache
    -0.40
     pleaſure
    -0.40
    Personendaten
    -0.39
     alicante
    -0.37
    новниш
    -0.35
    POSITIVE LOGITS
    THE
    0.61
    SOME
    0.59
    WHEN
    0.58
    JUST
    0.56
    FOR
    0.55
    WHAT
    0.54
    THERE
    0.54
    HOW
    0.54
    THIS
    0.54
    LIST
    0.53
    Activations Density 31.485%

    No Known Activations