© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7952
    Prev
    Next
    INDEX
    Explanations

    the word "bits" and the phrase "floating point"

    oai_token-act-pair · gemini-2.0-flash

    bits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    AndEndTag
    -0.64
     pinulongan
    -0.61
     finally
    -0.60
    AddHtmlAttribute
    -0.59
     dAtA
    -0.59
    ValueGeneration
    -0.59
    Географи
    -0.56
     ويكيميديا
    -0.55
    setViewName
    -0.55
    jsonwebtoken
    -0.54
    POSITIVE LOGITS
    gelen
    0.68
    Preset
    0.66
     ferons
    0.63
     débat
    0.63
    MEASURE
    0.63
     Formel
    0.61
    observe
    0.59
     bénéficiaire
    0.59
    Exposure
    0.58
     enfans
    0.58
    Activations Density 0.386%

    No Known Activations