© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8283
    Prev
    Next
    INDEX
    Explanations

    words that start sentences or clauses, and words that indicate causality or logical consequence.

    oai_token-act-pair · gemini-2.0-flash

    transition words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <eos>
    -1.30
    Rüyada
    -0.85
    RegressionTest
    -0.81
    참고
    -0.68
    Hozzáférés
    -0.66
    ↵↵
    -0.65
    fjspx
    -0.65
     resourceCulture
    -0.64
     &___
    -0.61
    Lähteet
    -0.60
    POSITIVE LOGITS
     myſelf
    1.12
     itſelf
    1.10
    ^(@)
    0.94
     themſelves
    0.86
    ſelf
    0.85
     raiſ
    0.81
     himſelf
    0.79
     pleaſure
    0.77
     Efq
    0.76
     Houſe
    0.75
    Activations Density 3.038%

    No Known Activations