© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 15422
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly C/C++ and possibly Go, including conditional statements, error handling, and function calls

    oai_token-act-pair · gemini-2.0-flash

    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_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
     Imagination
    -0.47
    GEBURTSDATUM
    -0.47
     whiteness
    -0.46
     dolls
    -0.46
    Incidence
    -0.45
    évaluateur
    -0.44
     bicycles
    -0.44
     wheelchairs
    -0.43
     Pots
    -0.43
     Incidence
    -0.43
    POSITIVE LOGITS
    featureID
    0.69
    PasswordEncoder
    0.58
    serviceWorker
    0.57
    Personendaten
    0.57
    webElementXpaths
    0.56
    contentLoaded
    0.55
    ttemberg
    0.54
     csrf
    0.52
    CastException
    0.51
    parsedMessage
    0.50
    Activations Density 8.840%

    No Known Activations