© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8577
    Prev
    Next
    INDEX
    Explanations

    the word "actual" and legal terms with the word "statements"

    oai_token-act-pair · gemini-2.0-flash

    actual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     theater
    -0.72
     theaters
    -0.69
     Theater
    -0.62
     theatre
    -0.61
    Theater
    -0.60
    icoot
    -0.58
     theatres
    -0.57
     Theaters
    -0.56
     Theatre
    -0.55
    ControllerAdvice
    -0.54
    POSITIVE LOGITS
    themselves
    0.70
    contentLoaded
    0.68
    herself
    0.66
     själva
    0.66
    Сам
    0.63
     selber
    0.61
    Insee
    0.60
    úsqueda
    0.59
     själv
    0.58
    itself
    0.58
    Activations Density 0.704%

    No Known Activations