© 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. 6568
    Prev
    Next
    INDEX
    Explanations

    words related to problems with software, especially debugging and fixing bugs

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word "despite"

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

    despite

    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
    oneofs
    -0.71
    aarrggbb
    -0.69
    PreferredItem
    -0.60
    quese
    -0.58
    Życiorys
    -0.58
    KommentareTeilen
    -0.58
    σουμε
    -0.57
    nls
    -0.56
    contentLoaded
    -0.56
     незавершена
    -0.55
    POSITIVE LOGITS
     despite
    2.20
    despite
    2.03
     spite
    1.89
     Despite
    1.74
     pesar
    1.67
     nonostante
    1.63
    Despite
    1.62
     несмотря
    1.59
     apesar
    1.57
     malgré
    1.51
    Activations Density 6.880%

    No Known Activations