© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8181
    Prev
    Next
    INDEX
    Explanations

    instances of the word "platform" (sometimes followed by "staff")

    oai_token-act-pair · gemini-2.0-flash

    platform

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    IntoConstraints
    -0.93
     AssemblyCulture
    -0.93
    Lähteet
    -0.93
    UnitTesting
    -0.84
     lenker
    -0.83
    #+#
    -0.81
    /*---
    -0.80
     pitié
    -0.80
    ionView
    -0.79
     feroit
    -0.77
    POSITIVE LOGITS
    ——
    0.54
    Commentary
    0.52
    órc
    0.52
    coda
    0.52
    enumi
    0.50
    '"
    0.50
    outre
    0.49
     facile
    0.49
     Whitehead
    0.49
     Freund
    0.48
    Activations Density 0.881%

    No Known Activations