© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11481
    Prev
    Next
    INDEX
    Explanations

    quantitative information (amounts, counts and sizes)

    oai_token-act-pair · gemini-2.0-flash

    numbers in words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    featureID
    -0.72
     desejo
    -0.42
     giud
    -0.41
     Wiktionnaire
    -0.41
    ialak
    -0.40
    הם
    -0.39
    Initializable
    -0.38
    AccessorTable
    -0.38
     ognuno
    -0.38
    JspWriter
    -0.37
    POSITIVE LOGITS
    archiviato
    0.74
    ſelves
    0.72
    ^(@)
    0.69
    contentLoaded
    0.68
    teries
    0.64
    ſelf
    0.64
    ISTAS
    0.64
     CreateTagHelper
    0.63
    inheritDoc
    0.63
    SourceChecksum
    0.63
    Activations Density 2.346%

    No Known Activations