© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5735
    Prev
    Next
    INDEX
    Explanations

    uses of the word "and" and nearby words

    oai_token-act-pair · gemini-2.0-flash

    coordinating conjunctions

    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
    .
    -0.48
     Throughout
    -0.42
    ंदीखरीदारी
    -0.40
    Throughout
    -0.39
    有
    -0.36
    Having
    -0.36
     Having
    -0.36
     Introduced
    -0.35
     Speaking
    -0.35
     People
    -0.34
    POSITIVE LOGITS
     nahilalakip
    0.88
    #+#
    0.77
    PreferredItem
    0.77
    ValueGeneration
    0.76
     Administrativna
    0.76
     Italijani
    0.75
    :✨
    0.72
     Whigs
    0.72
    @[+][
    0.71
     sherds
    0.69
    Activations Density 6.676%

    No Known Activations