© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 732
    Prev
    Next
    INDEX
    Explanations

    legal and courtroom terms

    oai_token-act-pair · gemini-2.0-flash

    French words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    line
    -0.58
    set
    -0.55
    op
    -0.55
    top
    -0.52
    net
    -0.52
    str
    -0.51
    bar
    -0.50
    go
    -0.50
    com
    -0.50
    val
    -0.50
    POSITIVE LOGITS
     fermés
    0.82
     avoient
    0.82
     peindre
    0.82
     stället
    0.81
     feroit
    0.81
     tromper
    0.80
     ouverts
    0.79
     extérieures
    0.79
     étoient
    0.78
     actuels
    0.78
    Activations Density 6.641%

    No Known Activations