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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4588
    Prev
    Next
    INDEX
    Explanations

    discourse markers and opinion words

    oai_token-act-pair · gemini-2.0-flash

    code-related terms and syntax patterns

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

    because

    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
    ')(
    -0.62
     [],
    -0.62
    "}")
    -0.60
    :],
    -0.57
    ")(
    -0.57
    ++]=
    -0.57
    trage
    -0.54
    >${
    -0.52
    ])):
    -0.51
    ']>
    -0.51
    POSITIVE LOGITS
     you
    0.73
    EndInit
    0.68
     I
    0.68
    webElementXpaths
    0.66
    RenderAtEndOf
    0.65
    ValueStyle
    0.65
     Paglinawan
    0.64
    ítő
    0.63
     GeoNames
    0.62
     @"/
    0.62
    Activations Density 2.598%

    No Known Activations