© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8737
    Prev
    Next
    INDEX
    Explanations

    names of people and places and words that are often nearby

    oai_token-act-pair · gemini-2.0-flash

    Religious/honorific titles

    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
     initComponents
    -0.60
    
    -0.60
    données
    -0.60
     चीज़ों
    -0.59
     AssemblyVersion
    -0.58
     informée
    -0.57
     autorytatywna
    -0.57
     newOwner
    -0.57
    yakarta
    -0.57
    AddHtmlAttribute
    -0.56
    POSITIVE LOGITS
     Chriftian
    0.68
     Majefty
    0.56
    EndContext
    0.55
     Efq
    0.54
     Jefus
    0.51
     fråga
    0.50
    hdys
    0.49
     Chrift
    0.49
     fathoms
    0.48
     Tử
    0.48
    Activations Density 2.229%

    No Known Activations