© 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. 7372
    Prev
    Next
    INDEX
    Explanations

    the word "an" followed by digits or dollar signs

    oai_token-act-pair · gemini-2.0-flash

    an

    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
     job
    -0.97
     mixture
    -0.96
     series
    -0.95
     survey
    -0.95
     career
    -0.94
     story
    -0.94
     reminder
    -0.94
     reaſon
    -0.93
     solution
    -0.93
     teacher
    -0.93
    POSITIVE LOGITS
     fumée
    0.68
     poussière
    0.66
     azioni
    0.59
     utilizzo
    0.58
     efficacité
    0.57
     nôtre
    0.55
     így
    0.54
     pouvoit
    0.54
     trouvera
    0.54
     bonté
    0.54
    Activations Density 0.701%

    No Known Activations