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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6359
    Prev
    Next
    INDEX
    Explanations

    pieces of code involving error handling and path resolution

    oai_token-act-pair · gemini-2.0-flash

    programming-related keywords

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

    res or req

    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
    بوابة
    -0.59
    Am
    -0.51
     téléphonique
    -0.49
     replying
    -0.49
     réponse
    -0.48
     answers
    -0.48
     réponses
    -0.48
    Subject
    -0.48
    Abr
    -0.47
     replies
    -0.47
    POSITIVE LOGITS
     يتيمه
    0.80
    ագրություններ
    0.77
     ComVisible
    0.64
    makeConstraints
    0.63
    NOPQRST
    0.63
     resourceCulture
    0.62
    WebVitals
    0.59
    SerializedSize
    0.58
    IsContent
    0.56
    HasIndex
    0.56
    Activations Density 1.282%

    No Known Activations