© 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. 4848
    Prev
    Next
    INDEX
    Explanations

    words related to levels or types of education

    oai_token-act-pair · gemini-2.0-flash

    the word "higher"

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

    higher

    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
     '\\;'
    -0.92
    aarrggbb
    -0.80
    Vidite
    -0.74
     estekak
    -0.73
     <=",
    -0.70
    
    -0.69
    jooq
    -0.68
     InputDecoration
    -0.66
     disambiguazione
    -0.66
    Sucesor
    -0.64
    POSITIVE LOGITS
    outchouc
    0.49
    出版年
    0.48
    initWithFrame
    0.45
    exec
    0.45
    EDGE
    0.44
     house
    0.43
     label
    0.43
    XmlElement
    0.42
    ørs
    0.42
    ashe
    0.41
    Activations Density 0.790%

    No Known Activations