© 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. 15207
    Prev
    Next
    INDEX
    Explanations

    words associated with statistical research and experiments

    oai_token-act-pair · gemini-2.0-flash

    Effects/impact

    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
     Numerade
    -0.73
    setVerticalGroup
    -0.73
    Personendaten
    -0.72
     '\\;'
    -0.72
     betweenstory
    -0.71
    transQ
    -0.71
    windowFixed
    -0.71
    paksa
    -0.71
    __':
    -0.70
    aarrggbb
    -0.69
    POSITIVE LOGITS
    on
    0.62
     Communauté
    0.49
    ality
    0.48
     on
    0.47
     upon
    0.47
    Autowired
    0.46
     União
    0.46
    شع
    0.46
    alities
    0.45
    estone
    0.45
    Activations Density 24.393%

    No Known Activations