© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 950
    Prev
    Next
    INDEX
    Explanations

    words relating to publishing like manuscript, papers, volumes, essays, material, stories, authors etc

    oai_token-act-pair · gemini-2.0-flash

    written works

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Personensuche
    -0.59
    Subject
    -0.58
    expandindo
    -0.56
    subject
    -0.54
     Subject
    -0.54
     subject
    -0.51
    utives
    -0.48
     SUBJECT
    -0.47
    POSE
    -0.47
     soggetti
    -0.46
    POSITIVE LOGITS
    GEBURTSDATUM
    0.70
    
    0.68
    MemoryWarning
    0.62
    idopsis
    0.58
    RRect
    0.56
    ruptedException
    0.56
     estekak
    0.54
     ModelExpression
    0.52
    /**
    0.51
     stanovnika
    0.51
    Activations Density 8.774%

    No Known Activations