© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7490
    Prev
    Next
    INDEX
    Explanations

    words commonly used in software documentation, code snippets, and technical discussions.

    oai_token-act-pair · gemini-2.0-flash

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    },[
    -0.53
    ÍC
    -0.51
     Walling
    -0.48
     Walton
    -0.48
    parsedMessage
    -0.48
    Espèce
    -0.47
     تانيه
    -0.47
    rostis
    -0.46
    siv
    -0.46
    rientes
    -0.46
    POSITIVE LOGITS
     AspNetCore
    0.71
    WithMany
    0.63
     InputDecoration
    0.56
    Sucesor
    0.56
     jsonify
    0.56
     argparse
    0.55
    PMailer
    0.55
     ViewHolder
    0.54
    setupUi
    0.54
     vôtre
    0.54
    Activations Density 15.581%

    No Known Activations