© 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. 15862
    Prev
    Next
    INDEX
    Explanations

    contractions and possessives using an apostrophe

    oai_token-act-pair · gemini-2.0-flash

    foreign text snippets

    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
    AsUp
    -0.96
     @"/
    -0.96
    +#+
    -0.89
     nahilalakip
    -0.86
     initComponents
    -0.86
     дописавши
    -0.83
    SourceChecksum
    -0.82
    Tikang
    -0.80
     ComVisible
    -0.79
    انيف
    -0.79
    POSITIVE LOGITS
     vectorielles
    0.74
     démocr
    0.71
     avoient
    0.69
     vectorielle
    0.65
     étoient
    0.64
     vertes
    0.64
     enfans
    0.64
     vérit
    0.62
     citoy
    0.60
     abstrait
    0.60
    Activations Density 0.986%

    No Known Activations