© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5645
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people and countries and financial terms, and punctuation

    oai_token-act-pair · gemini-2.0-flash

    specialized terms or jargon

    np_token-act-pair-logits · gpt-4o-mini

    People and their job 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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ioli
    -0.48
    Basta
    -0.46
    ule
    -0.45
     exile
    -0.44
     suffice
    -0.43
     basta
    -0.43
    ời
    -0.41
    estris
    -0.40
    olus
    -0.40
     glaring
    -0.40
    POSITIVE LOGITS
     سكانية
    0.79
    RectangleBorder
    0.75
     nakalista
    0.72
    SequentialGroup
    0.72
    ViewFeatures
    0.71
    abetes
    0.70
     Biôgrafia
    0.69
    Datuak
    0.69
     AssemblyProduct
    0.68
    InputBorder
    0.68
    Activations Density 0.319%

    No Known Activations