© 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. 3039
    Prev
    Next
    INDEX
    Explanations

    quantifiers and numbers

    oai_token-act-pair · 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
     CreateTagHelper
    -0.69
     wireType
    -0.67
     nahilalakip
    -0.60
    Koordinaten
    -0.57
    []
    
    -0.51
    TypeDefinition
    -0.51
    ConfigureAwait
    -0.50
     AssemblyCulture
    -0.50
     Visual
    -0.49
    tagext
    -0.48
    POSITIVE LOGITS
     winds
    0.63
     fires
    0.62
    andExpect
    0.54
    saraba
    0.54
    
    0.52
     planes
    0.51
    jLabel
    0.50
     auras
    0.50
     forces
    0.50
     breaths
    0.50
    Activations Density 2.376%

    No Known Activations