© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4032
    Prev
    Next
    INDEX
    Explanations

    text from programming languages and online forums, possibly specifically about escaping special characters

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "space"

    np_token-act-pair-logits · gpt-4o-mini

    space

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    SourceChecksum
    -0.67
    localctx
    -0.65
     defaultstate
    -0.62
     iNdEx
    -0.60
    mergeFrom
    -0.58
    sizeCache
    -0.56
    !("{}",
    -0.56
    NameInMap
    -0.55
    matchCondition
    -0.51
    OpenHelper
    -0.49
    POSITIVE LOGITS
     space
    1.34
     spaces
    1.32
    space
    1.22
     Space
    1.15
    Space
    1.14
     SPACE
    1.14
    spaces
    1.10
     Spaces
    1.07
    SPACE
    1.03
    Spaces
    0.99
    Activations Density 4.752%

    No Known Activations