© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5824
    Prev
    Next
    INDEX
    Explanations

    math terminology, especially terms related to mappings and spaces

    oai_token-act-pair · gemini-2.0-flash

    map

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -0.82
    AndEndTag
    -0.63
     Wikimedijinoj
    -0.61
     Roskov
    -0.57
    TagHelper
    -0.55
     mapping
    -0.55
     maps
    -0.54
     mappings
    -0.52
     AssemblyCulture
    -0.52
    цездатний
    -0.50
    POSITIVE LOGITS
    
    0.60
    iorgio
    0.60
    oredCriteria
    0.58
    ModelAndView
    0.57
    czegó
    0.54
    numerusform
    0.54
    INSEE
    0.53
     tän
    0.51
    orgio
    0.51
    sped
    0.50
    Activations Density 8.593%

    No Known Activations