© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 2477
    Prev
    Next
    INDEX
    Explanations

    snippets of code, URLs and/or stack traces

    oai_token-act-pair · gemini-2.0-flash

    common short words

    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
     vœux
    -0.80
     traités
    -0.80
     stället
    -0.78
     négociations
    -0.77
     varandra
    -0.76
     enfans
    -0.74
     âmes
    -0.74
     rayures
    -0.73
     avoient
    -0.73
     investissements
    -0.73
    POSITIVE LOGITS
     if
    0.36
     first
    0.33
     to
    0.32
     this
    0.32
     that
    0.32
     of
    0.31
     as
    0.31
     one
    0.31
     at
    0.31
     when
    0.31
    Activations Density 8.036%

    No Known Activations