Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14507
    Prev
    Next
    INDEX
    Explanations

    numbers or numeric characters in tables and other formatted lists or datasets

    oai_token-act-pair · gemini-2.0-flash

    Table data and calculations

    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
     lib
    -0.66
     Qu
    -0.64
    những
    -0.63
     Bor
    -0.62
     Bus
    -0.61
     qu
    -0.61
     Bos
    -0.61
     C
    -0.60
    tement
    -0.60
     She
    -0.58
    POSITIVE LOGITS
     Shakspeare
    0.90
     Offisielt
    0.79
     itſelf
    0.79
     uſ
    0.77
     Cæsar
    0.76
     noastre
    0.76
     myſelf
    0.75
     preſent
    0.73
     ſche
    0.73
     unſ
    0.71
    Activations Density 10.306%

    No Known Activations