© 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. 9051
    Prev
    Next
    INDEX
    Explanations

    the start of product descriptions or calculations

    oai_token-act-pair · gemini-2.0-flash

    product

    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
    IntoConstraints
    -0.96
    хьтан
    -0.95
     تانيه
    -0.94
     AssemblyCulture
    -0.91
     auffi
    -0.89
    webElementXpaths
    -0.85
     الرياضيه
    -0.85
    Personendaten
    -0.84
     SwitchCompat
    -0.82
    MigrationBuilder
    -0.82
    POSITIVE LOGITS
    ophyta
    0.43
     `
    0.41
    '
    0.41
     von
    0.40
     des
    0.40
    breng
    0.38
     Des
    0.38
     '
    0.37
    son
    0.36
     Lin
    0.36
    Activations Density 4.367%

    No Known Activations