© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 566
    Prev
    Next
    INDEX
    Explanations

    code-related markup such as attributes, namespaces, and tags.

    oai_token-act-pair · gemini-2.0-flash

    Code, programming

    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
     cherchés
    -0.85
    oa̍t
    -0.68
     kasarigan
    -0.63
     markets
    -0.60
     information
    -0.60
     resources
    -0.60
     entertainment
    -0.60
     types
    -0.60
     service
    -0.59
     podjela
    -0.59
    POSITIVE LOGITS
    parsedMessage
    0.58
    rxjs
    0.54
    WebDriver
    0.54
    Eloquent
    0.54
    Cryptography
    0.53
     onAnimation
    0.52
    Drupal
    0.49
    EntityFramework
    0.49
     sqlalchemy
    0.49
    UnitTesting
    0.48
    Activations Density 4.083%

    No Known Activations