© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13210
    Prev
    Next
    INDEX
    Explanations

    passages about making decisions and figuring things out

    oai_token-act-pair · gemini-2.0-flash

    determine

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    elemField
    -0.88
    PyExc
    -0.86
     Meksiku
    -0.86
    archiviato
    -0.86
    MLLoader
    -0.85
     يتيمه
    -0.84
    ^(@)
    -0.84
    .³
    -0.81
    Personendaten
    -0.81
     photolibrary
    -0.80
    POSITIVE LOGITS
     which
    0.77
     the
    0.62
     how
    0.60
     what
    0.59
    int
    0.52
     who
    0.50
     when
    0.49
     cui
    0.48
     as
    0.47
     Which
    0.47
    Activations Density 2.117%

    No Known Activations