© 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. 6346
    Prev
    Next
    INDEX
    Explanations

    content that looks like it might be from a web page including URLs, titles, menu items, tags, and a fair amount of noise

    oai_token-act-pair · gemini-2.0-flash

    its

    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
     myſelf
    -1.74
     quelcon
    -1.48
     whoſe
    -1.42
     ſeveral
    -1.41
     itſelf
    -1.40
     Monfieur
    -1.35
     vectorielles
    -1.34
     Efq
    -1.34
     ſhe
    -1.34
     avoient
    -1.34
    POSITIVE LOGITS
    ne
    0.87
    ta
    0.87
    y
    0.86
     ta
    0.85
    na
    0.85
    ba
    0.85
    ni
    0.83
    te
    0.82
    va
    0.82
    ci
    0.82
    Activations Density 3.680%

    No Known Activations