© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9805
    Prev
    Next
    INDEX
    Explanations

    the unit "pt", often used for font size, along with nearby numbers

    oai_token-act-pair · gemini-2.0-flash

    pt

    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
     (
    -0.99
    ↵↵
    -0.96
     
    -0.90
    a
    -0.79
     .
    -0.78
     I
    -0.77
     The
    -0.75
    <eos>
    -0.75
     [
    -0.72
    ,
    -0.72
    POSITIVE LOGITS
     myſelf
    1.38
    TypedDataSet
    1.37
     Efq
    1.34
     greateſt
    1.33
     $_"
    1.29
     photolibrary
    1.29
     ARXIV
    1.29
     ſtate
    1.27
     leaſt
    1.26
     pleaſure
    1.24
    Activations Density 1.683%

    No Known Activations