© 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. 5459
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a need for further study or action

    oai_token-act-pair · gemini-2.0-flash

    words indicating urgency or necessity

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

    necessary, required

    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
    naio
    -0.49
    Structured
    -0.48
    ibatis
    -0.48
    tettu
    -0.47
    うち
    -0.47
     AssemblyProduct
    -0.45
    Dislikes
    -0.43
     kunt
    -0.42
    ardown
    -0.42
     חיים
    -0.42
    POSITIVE LOGITS
     necessary
    1.91
    necessary
    1.70
     needed
    1.60
     required
    1.60
     Necessary
    1.59
    Necessary
    1.48
    required
    1.45
     NECESS
    1.41
     Needed
    1.38
     Required
    1.33
    Activations Density 1.032%

    No Known Activations