© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10620
    Prev
    Next
    INDEX
    Explanations

    a chemical called okadaic acid, some words related to developing communities, and details in personal profiles

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "ada"

    np_token-act-pair-logits · gpt-4o-mini

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    webElementXpaths
    -0.75
     فريبيس
    -0.70
    PMailer
    -0.66
     EconPapers
    -0.65
    XmlAccessType
    -0.63
    TagHelper
    -0.63
    Autoritní
    -0.62
    SceneManagement
    -0.62
     ModelExpression
    -0.60
     خارجية
    -0.60
    POSITIVE LOGITS
     fait
    0.51
    Carriera
    0.45
    rate
    0.44
     auto
    0.44
    uxxxx
    0.43
     Krieg
    0.42
    jek
    0.41
     un
    0.41
    GroupLayout
    0.41
    atto
    0.41
    Activations Density 0.912%

    No Known Activations