© 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
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1341
    Prev
    Next
    INDEX
    Explanations

    words related to reporting, documentation, tagging, labeling, or marking something

    oai_token-act-pair · gemini-2.0-flash

    labeling

    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
     label
    -0.80
     tag
    -0.77
     tagged
    -0.73
     Label
    -0.73
     labels
    -0.72
     tags
    -0.71
     etiquetas
    -0.65
    Labels
    -0.65
     labeling
    -0.65
    标记
    -0.65
    POSITIVE LOGITS
    ArrowToggle
    0.81
    ChildScrollView
    0.60
    ionario
    0.59
     <<<<<<<<<<<<<<
    0.56
    Xna
    0.55
    AsUp
    0.54
    iserie
    0.54
    ngdoc
    0.53
     parlour
    0.53
    Datuak
    0.52
    Activations Density 43.760%

    No Known Activations