© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10723
    Prev
    Next
    INDEX
    Explanations

    names and citations, particularly in legal and academic texts

    oai_token-act-pair · gemini-2.0-flash

    research papers and legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     otomatig
    -0.65
     viață
    -0.58
     favors
    -0.58
     Louisiana
    -0.57
    burg
    -0.57
     Alabama
    -0.56
     Ohio
    -0.56
     theater
    -0.56
     honoring
    -0.56
     Florida
    -0.55
    POSITIVE LOGITS
    behaviour
    0.95
     randomised
    0.94
     Behaviour
    0.94
     Programmes
    0.89
    Colours
    0.89
    colours
    0.87
    Behaviour
    0.86
     optimisation
    0.86
    coloured
    0.85
     recognisable
    0.85
    Activations Density 5.087%

    No Known Activations