© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2078
    Prev
    Next
    INDEX
    Explanations

    articles, talks, and essays

    oai_token-act-pair · gemini-2.0-flash

    Discussions and Conversations

    np_max-act-logits · 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
     as
    -0.51
    edly
    -0.34
     in
    -0.34
    ateness
    -0.33
    (©
    -0.33
     Most
    -0.32
    enumi
    -0.32
    Most
    -0.32
     venons
    -0.32
     никак
    -0.31
    POSITIVE LOGITS
    when
    1.07
     when
    1.02
     quando
    0.88
     WHEN
    0.88
     wanneer
    0.79
    WHEN
    0.79
    cuando
    0.79
     cuando
    0.77
    WriteTagHelper
    0.77
     bringing
    0.74
    Activations Density 11.424%

    No Known Activations