© 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
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10219
    Prev
    Next
    INDEX
    Explanations

    mentions of numbers or years, especially with a leading space

    oai_token-act-pair · gemini-2.0-flash

    Year counts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    LookAnd
    -0.93
    GEBURTSDATUM
    -0.80
     незавершена
    -0.77
     defaultstate
    -0.76
     beginnetje
    -0.73
    contentLoaded
    -0.72
     AssemblyCulture
    -0.71
    protoc
    -0.70
     وتسجيلات
    -0.69
    GraphicsUnit
    -0.67
    POSITIVE LOGITS
    RUnlock
    0.52
    gtk
    0.49
     confirmations
    0.47
     Pilate
    0.46
     gjen
    0.46
     clogs
    0.46
    c
    0.45
     Sacrifice
    0.45
     Dacia
    0.45
    h
    0.44
    Activations Density 0.646%

    No Known Activations