© 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. 2763
    Prev
    Next
    INDEX
    Explanations

    prepositions and articles, especially "in" and "the."

    oai_token-act-pair · gemini-2.0-flash

    general information

    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
     rhestr
    -0.81
     ddelweddau
    -0.77
    SourceChecksum
    -0.75
    saraba
    -0.67
     throats
    -0.66
    thood
    -0.65
     незавершена
    -0.64
    #+#
    -0.63
    PropertyGroup
    -0.62
    bability
    -0.62
    POSITIVE LOGITS
    odo
    0.39
    ieniem
    0.39
     min
    0.39
    mbalikan
    0.38
    ondo
    0.38
    tagHelper
    0.38
    love
    0.38
     merk
    0.37
     mimo
    0.35
     pes
    0.35
    Activations Density 0.125%

    No Known Activations