© 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. 4580
    Prev
    Next
    INDEX
    Explanations

    words related to measurements of real-world materials or areas

    oai_token-act-pair · gemini-2.0-flash

    area

    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
     jScrollPane
    -0.71
    MENAFN
    -0.70
    Попис
    -0.69
     jLabel
    -0.68
    AutoField
    -0.65
    SequentialGroup
    -0.65
    !*\
    -0.64
     Affiliations
    -0.64
    ніципа
    -0.64
    chappen
    -0.63
    POSITIVE LOGITS
     area
    2.56
    area
    2.25
     Area
    2.19
    Area
    2.19
     AREA
    2.05
    AREA
    1.80
     área
    1.73
     areas
    1.51
    areas
    1.43
     Areas
    1.40
    Activations Density 8.778%

    No Known Activations