© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14372
    Prev
    Next
    INDEX
    Explanations

    the word "unique" followed by a noun or words describing inventiveness or the imagination

    oai_token-act-pair · gemini-2.0-flash

    unique

    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
     unique
    -2.30
    unique
    -2.11
    Unique
    -2.09
     Unique
    -2.03
     unieke
    -1.71
     UNIQUE
    -1.70
     einzigartige
    -1.62
     uniqueness
    -1.59
    UNIQUE
    -1.52
     uniques
    -1.47
    POSITIVE LOGITS
     saites
    0.65
    RectangleBorder
    0.64
    ConstraintMaker
    0.64
     الحره
    0.62
    ViewImports
    0.61
     nakalista
    0.59
     mapStateToProps
    0.56
    TestingModule
    0.55
    Referències
    0.53
     ddelweddau
    0.53
    Activations Density 2.357%

    No Known Activations