© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 8702
    Prev
    Next
    INDEX
    Explanations

    mentions of construction, especially buildings or roads

    oai_token-act-pair · gemini-2.0-flash

    construction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     construction
    -2.56
     Construction
    -2.30
    Construction
    -2.28
    construction
    -2.19
     CONSTRUCTION
    -2.13
     constructions
    -1.89
    CONSTRUCTION
    -1.84
     construct
    -1.78
     construcción
    -1.73
     construc
    -1.70
    POSITIVE LOGITS
     Belf
    0.56
     bereavement
    0.52
     CURIAM
    0.51
    ipot
    0.47
    orsese
    0.47
    Requis
    0.46
    illoma
    0.46
     AssemblyCulture
    0.45
    XmlAccessorType
    0.45
    UObject
    0.45
    Activations Density 1.053%

    No Known Activations