© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10348
    Prev
    Next
    INDEX
    Explanations

    mentions of programming languages or build environments and seemingly random artifacts involving letters and numbers.

    oai_token-act-pair · gemini-2.0-flash

    programming and data

    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
    hésite
    -0.57
    émission
    -0.57
    épisode
    -0.52
    queryInterface
    -0.48
     NSCoder
    -0.48
    icône
    -0.47
    enfance
    -0.47
    extrême
    -0.47
    indépendance
    -0.46
    empereur
    -0.46
    POSITIVE LOGITS
    amet
    0.65
    ado
    0.65
    acon
    0.64
    amo
    0.64
    adf
    0.63
    aju
    0.63
    aj
    0.62
    aden
    0.61
    aji
    0.61
    ajo
    0.61
    Activations Density 15.534%

    No Known Activations