© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7391
    Prev
    Next
    INDEX
    Explanations

    the letters "at" within words, especially followed by other letters

    oai_token-act-pair · gemini-2.0-flash

    chemistry/manufacturing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    NameInMap
    -0.67
    CopyWith
    -0.58
    ure
    -0.57
    ory
    -0.56
     RouterModule
    -0.56
    ura
    -0.53
    ed
    -0.52
    URE
    -0.52
    teries
    -0.52
    πάρχ
    -0.51
    POSITIVE LOGITS
     crossorigin
    0.66
    TagMode
    0.60
    AnchorStyles
    0.57
    cshtml
    0.53
     AssemblyCulture
    0.50
     nakalista
    0.50
    cmdline
    0.47
    ggish
    0.47
    ęcia
    0.46
    SqlServer
    0.46
    Activations Density 2.146%

    No Known Activations