© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8630
    Prev
    Next
    INDEX
    Explanations

    labels, numbers, and section headings relating to scientific studies

    oai_token-act-pair · gemini-2.0-flash

    archaic or old-fashioned text

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

    Introduction sections

    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
     but
    -0.54
     read
    -0.54
     post
    -0.51
    avedra
    -0.50
     fore
    -0.49
     further
    -0.49
     ex
    -0.49
     Here
    -0.48
     then
    -0.48
     string
    -0.48
    POSITIVE LOGITS
     Diſ
    0.98
     Eſ
    0.90
     itſelf
    0.88
     Anſ
    0.88
     Monfieur
    0.87
     Reſ
    0.86
     pleaſure
    0.85
    ſelf
    0.85
     greateſt
    0.84
     Jefus
    0.82
    Activations Density 9.928%

    No Known Activations