© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 501
    Prev
    Next
    INDEX
    Explanations

    words that can indicate a contrast is being made

    oai_token-act-pair · gemini-2.0-flash

    research/studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Lähteet
    -0.60
     lenker
    -0.58
    AddTagHelper
    -0.57
    eburger
    -0.55
    documentclass
    -0.54
    таратура
    -0.54
    出版年
    -0.54
    Cubit
    -0.51
    transQ
    -0.49
    <%@
    -0.49
    POSITIVE LOGITS
    uação
    0.60
     paio
    0.55
    __(/*!
    0.53
     prezent
    0.52
     inkl
    0.50
    "?>
    0.49
    romeda
    0.49
     russes
    0.48
     Potosí
    0.48
    Mentions
    0.48
    Activations Density 1.863%

    No Known Activations