© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14439
    Prev
    Next
    INDEX
    Explanations

    punctuation and verbs that could signal events happening to people

    oai_token-act-pair · gemini-2.0-flash

    comma

    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
    abestanden
    -0.68
     pinulongan
    -0.63
    IBOutlet
    -0.57
    Parcelize
    -0.54
     onPostExecute
    -0.52
    sous
    -0.52
     Sinon
    -0.49
     Nauka
    -0.48
     AssemblyCulture
    -0.47
    guten
    -0.47
    POSITIVE LOGITS
    RegressionTest
    0.74
     AssemblyCompany
    0.59
    AfterClass
    0.55
    っこう
    0.54
    <bos>
    0.54
    tanleria
    0.53
    rawDesc
    0.53
     Schließlich
    0.53
    RegistryLite
    0.52
    ObjectMeta
    0.52
    Activations Density 6.186%

    No Known Activations