© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2102
    Prev
    Next
    INDEX
    Explanations

    terms related to software development and user interface actions

    oai_token-act-pair · gemini-2.0-flash

    close or cancel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     cancel
    -0.81
     canceled
    -0.74
     cancellation
    -0.74
     cancelled
    -0.73
     cancels
    -0.69
    Cancel
    -0.69
     canceling
    -0.69
    cancel
    -0.68
     Cancel
    -0.67
     cancelling
    -0.66
    POSITIVE LOGITS
    Jeografia
    0.66
     confronti
    0.63
    RegressionTest
    0.61
    ForValue
    0.60
     gainera
    0.58
     larmes
    0.57
     mínima
    0.56
     OMITBAD
    0.54
     fallu
    0.54
     fisuras
    0.53
    Activations Density 20.423%

    No Known Activations