© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5606
    Prev
    Next
    INDEX
    Explanations

    uses of numeric data and related words in statistical analysis

    oai_token-act-pair · gemini-2.0-flash

    keywords related to content

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

    research and statistical analysis

    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
    toplasm
    -0.56
    rishnan
    -0.55
     avoit
    -0.54
     greateſt
    -0.53
     Ingles
    -0.52
     Coliseum
    -0.52
    блица
    -0.51
    utenant
    -0.50
     paces
    -0.50
    ensos
    -0.50
    POSITIVE LOGITS
     disambiguazione
    0.86
    DockStyle
    0.60
     content
    0.59
    content
    0.52
    webElementXpaths
    0.52
    Content
    0.51
     Content
    0.50
     bezeichneter
    0.50
     页
    0.48
     Infórmanos
    0.47
    Activations Density 1.588%

    No Known Activations