© 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. 3987
    Prev
    Next
    INDEX
    Explanations

    the word "domain"

    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
    Slf
    -0.69
    tagext
    -0.68
    XmlAccessType
    -0.68
     supérieurs
    -0.59
     présentés
    -0.59
     segíts
    -0.57
     fermés
    -0.57
    iseta
    -0.57
     GenerationType
    -0.56
     rapides
    -0.56
    POSITIVE LOGITS
     Tats
    0.69
    źdz
    0.69
    óng
    0.66
    !
    0.64
    ])]
    0.62
    Brainz
    0.62
    nessed
    0.61
    "]="
    0.61
    ributions
    0.60
     Gep
    0.60
    Activations Density 1.526%

    No Known Activations