© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14688
    Prev
    Next
    INDEX
    Explanations

    terms relating to medical or scientific research or legal proceedings

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     ‘
    -0.54
     
    -0.53
     dis
    -0.50
    guez
    -0.49
     in
    -0.48
     what
    -0.47
     A
    -0.46
     helyez
    -0.45
     talál
    -0.45
     it
    -0.45
    POSITIVE LOGITS
     pleaſure
    0.95
     houſe
    0.95
    GEBURTSDATUM
    0.94
     myſelf
    0.94
     Reſ
    0.94
     leſs
    0.91
     Shakspeare
    0.91
     Anſ
    0.90
     ſever
    0.90
     leaſt
    0.89
    Activations Density 2.626%

    No Known Activations