© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16099
    Prev
    Next
    INDEX
    Explanations

    the word pairings "so that" and phrases that show a cause and effect relationship

    oai_token-act-pair · gemini-2.0-flash

    so/to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    unkt
    -0.49
    trä
    -0.47
     оригинала
    -0.46
    kari
    -0.45
    ied
    -0.45
    тона
    -0.44
     popping
    -0.43
    Invert
    -0.42
    zeug
    -0.41
     decaying
    -0.41
    POSITIVE LOGITS
    MENAFN
    0.98
     propOrder
    0.87
    AddTagHelper
    0.83
    Personendaten
    0.80
    Tikang
    0.80
    webElementXpaths
    0.79
    IsContent
    0.72
    AndroidJUnit
    0.70
     ComVisible
    0.69
     "..\..\..\
    0.66
    Activations Density 1.073%

    No Known Activations