© 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. 13154
    Prev
    Next
    INDEX
    Explanations

    the word "object" used in a coding context

    oai_token-act-pair · gemini-2.0-flash

    object

    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
     object
    -2.45
    object
    -2.45
     Object
    -1.70
    Object
    -1.58
     objects
    -1.54
     objeto
    -1.43
    OBJECT
    -1.43
     OBJECT
    -1.41
    objects
    -1.34
     Objects
    -1.21
    POSITIVE LOGITS
     виправивши
    0.67
    Tembelea
    0.65
     betweenstory
    0.56
    Equations
    0.55
    FlatList
    0.54
    Jeografia
    0.52
     türlü
    0.52
    Explicación
    0.52
    twimg
    0.52
    dolu
    0.52
    Activations Density 0.745%

    No Known Activations