© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13119
    Prev
    Next
    INDEX
    Explanations

    building multi-liners address

    oai_token-act-pair · gemini-2.0-flash

    buildings and locations

    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
     оригіналу
    -0.70
     arşivlendi
    -0.68
    ंदीखरीदारी
    -0.63
    enderror
    -0.56
    ExecuteReader
    -0.54
    lorette
    -0.54
    HtmlAttribute
    -0.53
    IsPostBack
    -0.52
     createState
    -0.52
    GOTREF
    -0.52
    POSITIVE LOGITS
     ComVisible
    0.57
    Aholisi
    0.55
     autorytatywna
    0.54
     spreken
    0.50
     gebeten
    0.48
     Eliot
    0.47
     âmes
    0.47
     traditionnels
    0.47
     artificiales
    0.46
     couverts
    0.46
    Activations Density 1.590%

    No Known Activations