© 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. 5346
    Prev
    Next
    INDEX
    Explanations

    words and phrases used to emphasize descriptions

    oai_token-act-pair · gemini-2.0-flash

    terms related to notable individuals

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

    famous person

    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
    bootstrapcdn
    -0.78
    новниш
    -0.70
    SharedCtor
    -0.64
     définiti
    -0.61
    XmlAccessType
    -0.60
    liosis
    -0.59
    ########.
    -0.59
     néz
    -0.57
    InitVars
    -0.57
    脚注の使い方
    -0.57
    POSITIVE LOGITS
    HtmlAttribute
    0.64
     famous
    0.60
     influential
    0.58
     noqa
    0.56
     renowned
    0.56
    nocache
    0.54
     famed
    0.52
     revered
    0.51
     talented
    0.51
    tal
    0.50
    Activations Density 2.196%

    No Known Activations