© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15630
    Prev
    Next
    INDEX
    Explanations

    words related to civil engineering and infrastructure projects involving water.

    oai_token-act-pair · gemini-2.0-flash

    water systems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    expandindo
    -0.81
     disambiguazione
    -0.79
     ujednoznacz
    -0.76
    PRNewswire
    -0.72
    parsedMessage
    -0.70
    phosa
    -0.69
    المكان
    -0.69
     متعلقه
    -0.69
     مرئيه
    -0.69
     Paglinawan
    -0.67
    POSITIVE LOGITS
     lines
    0.44
     garanzia
    0.43
    se
    0.42
    fetchone
    0.42
     commerciales
    0.41
    \{\\
    0.41
     bas
    0.40
    舍
    0.40
     shafts
    0.40
     abuelos
    0.40
    Activations Density 3.960%

    No Known Activations