© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1607
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to user accounts and text messaging

    oai_token-act-pair · gemini-2.0-flash

    website code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    yntaxException
    -0.59
    GeneratedCode
    -0.47
     les
    -0.41
     disco
    -0.41
    莱
    -0.40
    RegressionTest
    -0.40
    WithEmail
    -0.39
     ExecuteAsync
    -0.39
     cool
    -0.39
    rial
    -0.39
    POSITIVE LOGITS
     wikipagina
    0.74
    oglio
    0.65
    IBOutlet
    0.63
    SequentialGroup
    0.62
    \{\\
    0.62
     normaux
    0.61
    zzleHttp
    0.61
     dreamstime
    0.59
    tubers
    0.59
    writerow
    0.59
    Activations Density 0.565%

    No Known Activations