© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13690
    Prev
    Next
    INDEX
    Explanations

    single and multi-character acronyms and abbreviations

    oai_token-act-pair · gemini-2.0-flash

    Abbreviations/codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     ارز
    -0.54
    dro
    -0.43
    udd
    -0.42
    uti
    -0.42
    isma
    -0.41
    ss
    -0.41
     Gaye
    -0.41
    ord
    -0.41
     Carriers
    -0.41
    fü
    -0.41
    POSITIVE LOGITS
    AddTagHelper
    0.85
     disambiguazione
    0.71
     bezeichneter
    0.67
    AndEndTag
    0.66
     insuffisamment
    0.65
    AnimationsModule
    0.65
    SequentialGroup
    0.64
     MainAxisSize
    0.63
    TagMode
    0.63
     itſelf
    0.63
    Activations Density 2.822%

    No Known Activations