© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12308
    Prev
    Next
    INDEX
    Explanations

    words associated with classifying things into categories

    oai_token-act-pair · gemini-2.0-flash

    categorization

    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
     category
    -2.38
     Category
    -2.19
     categories
    -2.16
     Categories
    -2.11
    Category
    -2.11
     classification
    -2.06
     Classification
    -2.06
     CATEGORY
    -2.02
    Classification
    -1.98
    category
    -1.95
    POSITIVE LOGITS
    invokeLater
    0.67
    
    0.54
    BeginContext
    0.52
    bewerken
    0.52
     c
    0.52
    getMenuInflater
    0.52
    HtmlAttribute
    0.51
    بوابة
    0.48
    GEBURTSDATUM
    0.48
     insuffisamment
    0.48
    Activations Density 2.415%

    No Known Activations