© 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. 11580
    Prev
    Next
    INDEX
    Explanations

    words adjacent to the word "said" and some other words related to attributing quotes.

    oai_token-act-pair · gemini-2.0-flash

    technical terms or concepts

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

    said

    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
     of
    -0.56
    1
    -0.47
    i
    -0.46
    or
    -0.46
    bu
    -0.45
    ten
    -0.44
     olduk
    -0.44
    8
    -0.44
    p
    -0.44
    n
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    1.08
    DockStyle
    1.02
     BoxFit
    0.92
     AssemblyCulture
    0.91
    IsContent
    0.89
    VersionUID
    0.85
    verwijspagina
    0.84
    )";
    0.83
     مشين
    0.83
    AnchorStyles
    0.82
    Activations Density 3.049%

    No Known Activations