© 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. 11485
    Prev
    Next
    INDEX
    Explanations

    scientific publication citations, including journal names, volume/issue numbers, and page ranges

    oai_token-act-pair · gemini-2.0-flash

    scientific papers

    np_max-act-logits · gemini-2.0-flash
    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
    tache
    -0.56
    our
    -0.49
     defire
    -0.49
    loadModel
    -0.49
     Malk
    -0.48
    akse
    -0.48
    canestro
    -0.45
    hips
    -0.45
    graphy
    -0.45
    boats
    -0.44
    POSITIVE LOGITS
    ंदीखरीदारी
    0.72
    RegistryLite
    0.69
     كومونز
    0.63
    -
    0.61
     EconPapers
    0.60
    AddHtmlAttribute
    0.59
    Portale
    0.59
    Descripció
    0.54
    jsxFileName
    0.54
    InitVars
    0.54
    Activations Density 13.983%

    No Known Activations