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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14970
    Prev
    Next
    INDEX
    Explanations

    citations and legal references

    oai_token-act-pair · gemini-2.0-flash

    number 7

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     propOrder
    -0.71
     five
    -0.60
    ⑤
    -0.59
    ]")]
    -0.59
     ५
    -0.58
    findpost
    -0.57
     cinque
    -0.55
     keempat
    -0.55
     four
    -0.55
     fifth
    -0.55
    POSITIVE LOGITS
    7
    0.79
     seventh
    0.76
     Seventh
    0.72
    Seventh
    0.72
     Seven
    0.70
     VII
    0.68
    ContentAsync
    0.67
     七
    0.65
    Xaml
    0.65
     SEVEN
    0.62
    Activations Density 6.883%

    No Known Activations