© 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. 11859
    Prev
    Next
    INDEX
    Explanations

    code related to exceptions, and looping

    oai_token-act-pair · gemini-2.0-flash

    error handling keywords

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

    catch

    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
    1
    -0.58
    v
    -0.57
    int
    -0.56
    man
    -0.55
    N
    -0.53
    j
    -0.53
    vie
    -0.52
    z
    -0.51
    set
    -0.51
    本
    -0.50
    POSITIVE LOGITS
    học
    0.81
    ^(@)
    0.77
    trường
    0.72
    dây
    0.72
    leſs
    0.71
    nhung
    0.66
     pauvres
    0.66
    Cordialement
    0.65
    couvrez
    0.65
     stället
    0.65
    Activations Density 0.340%

    No Known Activations