© 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. 11634
    Prev
    Next
    INDEX
    Explanations

    articles and sentences started with the word "the"

    oai_token-act-pair · gemini-2.0-flash

    the

    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
     Purpose
    -0.78
     rest
    -0.77
     purpose
    -0.72
     Purposes
    -0.68
    Purpose
    -0.68
    purpose
    -0.66
    scriptcase
    -0.65
     purposes
    -0.63
    LookAnd
    -0.63
    UnusedPrivate
    -0.62
    POSITIVE LOGITS
     for
    0.70
    for
    0.54
    Décès
    0.49
     Mexique
    0.43
    感じが
    0.42
    meck
    0.42
    grado
    0.42
     aspetta
    0.42
     Thieves
    0.41
    shang
    0.41
    Activations Density 5.483%

    No Known Activations