© 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. 2026
    Prev
    Next
    INDEX
    Explanations

    words associated with data analysis, research, and scientific publications

    oai_token-act-pair · gemini-2.0-flash

    multiple

    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
    DoubleQuotes
    -0.76
    TagMode
    -0.74
    +#+#
    -0.71
     <<<<<<<<<<<<<<
    -0.64
    QMetaType
    -0.60
    aarrggbb
    -0.56
     disponibilités
    -0.53
    igshid
    -0.51
     Several
    -0.50
    Several
    -0.50
    POSITIVE LOGITS
     multiple
    2.63
    multiple
    2.31
     Multiple
    2.30
    Multiple
    2.22
     MULTIPLE
    2.05
    MULTIPLE
    1.70
     multiples
    1.47
     múltiples
    1.34
     múltip
    1.22
     múltiple
    1.15
    Activations Density 18.354%

    No Known Activations