© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3593
    Prev
    Next
    INDEX
    Explanations

    mentions of numbers, especially small numbers

    oai_token-act-pair · gemini-2.0-flash

    numbers

    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
     препратки
    -0.63
    boten
    -0.61
    ztal
    -0.59
    zzar
    -0.59
     AssemblyCulture
    -0.58
    jarse
    -0.57
    bewerken
    -0.56
     depositphotos
    -0.56
    webElement
    -0.56
     auffi
    -0.54
    POSITIVE LOGITS
     Roads
    0.52
     الحره
    0.51
     Réponses
    0.50
    帖最后由
    0.46
     spectra
    0.44
     Sites
    0.43
     gutters
    0.43
     Classes
    0.43
     Un
    0.42
    Roads
    0.42
    Activations Density 5.376%

    No Known Activations