© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1607
    Prev
    Next
    INDEX
    Explanations

    technical language relating to biological or chemical processes

    oai_token-act-pair · gemini-2.0-flash

    scientific procedures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    WHO
    -0.50
     quyền
    -0.49
     lixo
    -0.48
    kN
    -0.46
    behaviour
    -0.46
     resol
    -0.45
     delinquency
    -0.45
    rifts
    -0.45
    Behaviour
    -0.44
    olume
    -0.44
    POSITIVE LOGITS
     process
    0.95
     Process
    0.86
     processes
    0.85
     Processes
    0.84
    Processes
    0.83
    process
    0.81
    Process
    0.76
     PROCESS
    0.75
    processes
    0.74
     PROCESSES
    0.74
    Activations Density 2.737%

    No Known Activations