© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16220
    Prev
    Next
    INDEX
    Explanations

    the word "action" (capitalized or not) in contexts ranging from computer programming and software systems to human behavior and news titles.

    oai_token-act-pair · gemini-2.0-flash

    action

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     hæ
    -0.45
    testcase
    -0.44
     agujas
    -0.43
    円
    -0.43
     Engle
    -0.43
    Domains
    -0.42
    lawesi
    -0.42
     watu
    -0.42
    Bibliografie
    -0.42
    rozco
    -0.41
    POSITIVE LOGITS
     "..\..\..\
    0.71
    NUMX
    0.71
    addCriterion
    0.68
    WithIOException
    0.67
    UnusedPrivate
    0.66
    Hochspringen
    0.65
    elemField
    0.63
    RectangleBorder
    0.63
    StructEnd
    0.62
    hdashline
    0.61
    Activations Density 3.441%

    No Known Activations