© 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. 15398
    Prev
    Next
    INDEX
    Explanations

    research or academic language related to a variety of topics like biology or computer science.

    oai_token-act-pair · gemini-2.0-flash

    Fluids and flow

    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
     Flow
    -1.82
    Flow
    -1.72
     flow
    -1.70
     Flows
    -1.63
    flow
    -1.63
     FLOW
    -1.59
     flows
    -1.53
     Pump
    -1.50
    Pump
    -1.50
     pump
    -1.48
    POSITIVE LOGITS
     urbanos
    0.46
    ReactDOM
    0.46
     acetyl
    0.45
    Versión
    0.45
    rovna
    0.44
    cci
    0.44
     Corbu
    0.43
     oxides
    0.43
    lsen
    0.42
    styleable
    0.42
    Activations Density 2.029%

    No Known Activations