© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 7376
    Prev
    Next
    INDEX
    Explanations

    data from scientific research, especially about medicine or computer software

    oai_token-act-pair · gemini-2.0-flash

    Code descriptions

    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
     analysis
    -1.08
     description
    -1.05
     explanation
    -1.02
     review
    -0.99
     discussion
    -0.99
     presentation
    -0.98
     information
    -0.96
     application
    -0.95
    description
    -0.93
     reference
    -0.93
    POSITIVE LOGITS
     dirt
    0.57
     flat
    0.56
     grass
    0.55
     barefoot
    0.55
     flats
    0.55
     hungry
    0.54
     wind
    0.53
     dead
    0.52
     wings
    0.52
     dry
    0.52
    Activations Density 9.562%

    No Known Activations