© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12937
    Prev
    Next
    INDEX
    Explanations

    variations of the phrase "had been"

    oai_token-act-pair · gemini-2.0-flash

    been

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     been
    -1.61
    been
    -1.55
    Been
    -1.36
     BEEN
    -1.31
     Been
    -1.21
     vært
    -0.73
     sido
    -0.72
     été
    -0.71
     været
    -0.70
     varit
    -0.70
    POSITIVE LOGITS
    StreetMap
    0.66
    ittens
    0.62
    lieri
    0.61
    parsedMessage
    0.61
    Geographie
    0.60
    AndroidJUnit
    0.60
    =$((
    0.60
    хьтан
    0.60
    MemoryWarning
    0.60
    ContentAsync
    0.60
    Activations Density 0.220%

    No Known Activations