© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13852
    Prev
    Next
    INDEX
    Explanations

    references to treaties, agreements, and conventions, especially related to specific locations or dates

    oai_token-act-pair · gemini-2.0-flash

    treaties and locations

    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
     of
    -0.47
    ,
    -0.47
     area
    -0.45
     non
    -0.44
     alternate
    -0.43
    ?
    -0.43
     alternative
    -0.42
     di
    -0.42
    .
    -0.42
    μη
    -0.41
    POSITIVE LOGITS
    ContentAsync
    0.93
    saraba
    0.90
     AssemblyCulture
    0.90
    InputBorder
    0.89
     kasarigan
    0.89
    IndentedString
    0.88
    Geplaatst
    0.86
     AttributeSet
    0.85
    AddTagHelper
    0.85
    IsContent
    0.85
    Activations Density 0.542%

    No Known Activations