© 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. 7365
    Prev
    Next
    INDEX
    Explanations

    code snippets or code-related keywords

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    console
    -1.83
     console
    -1.78
    Console
    -1.36
     Console
    -1.32
     consoles
    -1.27
    alert
    -1.14
    println
    -1.02
     consola
    -1.02
    CONSOLE
    -0.91
     undefined
    -0.91
    POSITIVE LOGITS
    TagMode
    0.67
    AndroidJUnit
    0.50
    cesi
    0.48
    /***/
    0.47
    findpost
    0.47
    BagLayout
    0.47
    aites
    0.46
     subsidized
    0.45
    ruler
    0.45
    égorie
    0.45
    Activations Density 2.284%

    No Known Activations