© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 291
    Prev
    Next
    INDEX
    Explanations

    a combination of various domain-specific and math text

    oai_token-act-pair · gemini-2.0-flash

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     transfieras
    -0.66
     nonUne
    -0.64
     noDo
    -0.63
    Erreferentziak
    -0.60
    BeginContext
    -0.60
     الحره
    -0.57
     pinulongan
    -0.55
     חיצוניים
    -0.54
     payé
    -0.52
    DockStyle
    -0.52
    POSITIVE LOGITS
     Genu
    0.52
     distal
    0.52
    WebControls
    0.51
    eavor
    0.49
     karş
    0.49
     '&#
    0.48
    Coup
    0.46
    воз
    0.45
     vuelven
    0.45
     Dist
    0.45
    Activations Density 0.836%

    No Known Activations