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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9803
    Prev
    Next
    INDEX
    Explanations

    the word "domain" or terms in the context of tokens and commands

    oai_token-act-pair · gemini-2.0-flash

    domain

    np_max-act · gemini-2.0-flash

    domain

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    )");
    -0.88
    .";
    -0.77
     """
    -0.74
    .",
    -0.73
    itism
    -0.72
     likes
    -0.71
    awtextra
    -0.70
    /−
    -0.70
    sune
    -0.69
    ogh
    -0.68
    POSITIVE LOGITS
    ंदीखरीदारी
    0.87
     ISNI
    0.73
    TableHead
    0.64
    iglesia
    0.60
     zelve
    0.58
    Auckland
    0.57
     её
    0.57
    WriteBarrier
    0.56
     hanem
    0.55
     optimise
    0.54
    Activations Density 1.536%

    No Known Activations