© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13531
    Prev
    Next
    INDEX
    Explanations

    abbreviations consisting of multiple capital letters, especially those relating to medical research and disorders.

    oai_token-act-pair · gemini-2.0-flash

    Acronyms in technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     autorytatywna
    -0.92
    XmlAccessorType
    -0.80
    WebVitals
    -0.78
    ViewFeatures
    -0.73
    Cyfeiriadau
    -0.72
     disambiguazione
    -0.68
    bootstrapcdn
    -0.67
    
    -0.67
    <?
    -0.66
    الحياه
    -0.66
    POSITIVE LOGITS
     getP
    1.19
     P
    1.16
     PS
    1.12
     p
    1.12
     PP
    1.10
    getP
    1.09
    PS
    1.07
     PN
    1.07
    PB
    1.06
     PB
    1.06
    Activations Density 15.734%

    No Known Activations