© 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. 9432
    Prev
    Next
    INDEX
    Explanations

    the word "first" and also words that signal the start of a numbered list or question

    oai_token-act-pair · gemini-2.0-flash

    First

    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
    imi
    -0.50
     QtWidgets
    -0.47
    iren
    -0.46
    ite
    -0.46
    ig
    -0.45
    tih
    -0.44
    ep
    -0.44
    ir
    -0.43
    ge
    -0.42
    ited
    -0.42
    POSITIVE LOGITS
    GTCX
    0.72
    Vidite
    0.69
     Réponses
    0.69
    parsedMessage
    0.67
     الحره
    0.67
    )";
    0.65
    Personensuche
    0.65
     تضيفلها
    0.65
    UserScript
    0.63
    IUrlHelper
    0.62
    Activations Density 16.433%

    No Known Activations