© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 13230
    Prev
    Next
    INDEX
    Explanations

    words related to chemistry and materials science

    oai_token-act-pair · gemini-2.0-flash

    chemical compounds

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    клопе
    -0.70
    JvmStatic
    -0.66
    Демографія
    -0.59
    prefixer
    -0.59
     مشين
    -0.57
    ')";
    -0.56
     ModelExpression
    -0.55
    CardBody
    -0.52
     """
    
    -0.52
     насељу
    -0.52
    POSITIVE LOGITS
    MessageOf
    0.68
    rungsseite
    0.54
    textTheme
    0.52
    
    0.52
     ferro
    0.51
    
    0.50
    Przypisy
    0.49
     tetrachloride
    0.49
     metab
    0.49
    MemoryWarning
    0.48
    Activations Density 5.190%

    No Known Activations