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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7358
    Prev
    Next
    INDEX
    Explanations

    text written in a mix of English and Spanish, especially related to technical topics and programming

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash

    Spanish function words

    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_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
     ویکی‌پدیا
    -0.55
     top
    -0.45
    richTextPanel
    -0.44
     خارجية
    -0.42
    Top
    -0.40
    日閲覧
    -0.39
    UserScript
    -0.37
     leis
    -0.36
    RepeatedField
    -0.36
     consumi
    -0.36
    POSITIVE LOGITS
    taminophen
    0.66
    kuuta
    0.65
    ChildIndex
    0.64
     InputDecoration
    0.63
    มาะ
    0.62
    numerusform
    0.60
    isContained
    0.59
    ---+
    0.59
    Relevance
    0.58
    KommentareTeilen
    0.58
    Activations Density 2.012%

    No Known Activations