© 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. 9369
    Prev
    Next
    INDEX
    Explanations

    the word "a" preceded by various words in informal dialogue

    oai_token-act-pair · gemini-2.0-flash

    a

    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
    égard
    -0.55
    fraid
    -0.54
    corns
    -0.51
    humanité
    -0.50
    actualité
    -0.49
    enfance
    -0.48
    unité
    -0.48
    ();
    -0.48
    warded
    -0.47
    attente
    -0.47
    POSITIVE LOGITS
     oignon
    0.72
     NSCoder
    0.69
     église
    0.69
     Australie
    0.69
     autorité
    0.68
     occasione
    0.68
     resourceCulture
    0.67
     appointment
    0.66
     EconPapers
    0.66
     abbandon
    0.65
    Activations Density 4.840%

    No Known Activations