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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6056
    Prev
    Next
    INDEX
    Explanations

    text about food and events

    oai_token-act-pair · gemini-2.0-flash

    packaging-related terms

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

    Containers

    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
    parsedMessage
    -0.76
     GenerationType
    -0.69
    CloseOperation
    -0.68
    примеча
    -0.65
    StoryboardSegue
    -0.64
     gyhoeddwyd
    -0.62
    protoimpl
    -0.62
    ModelAdmin
    -0.61
    bleau
    -0.60
     becauſe
    -0.60
    POSITIVE LOGITS
     box
    0.88
     boxes
    0.84
     package
    0.84
     packages
    0.83
     Box
    0.75
    Box
    0.72
     BOX
    0.72
     basket
    0.72
    box
    0.71
     bag
    0.71
    Activations Density 1.249%

    No Known Activations