© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14632
    Prev
    Next
    INDEX
    Explanations

    lines added or removed containing code related to operating system conditional compilation related to BSD

    oai_token-act-pair · gemini-2.0-flash

    diff symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    getRuntime
    -0.87
     CWE
    -0.73
    autogui
    -0.70
     Meksiku
    -0.70
    ništ
    -0.66
    StoryboardSegue
    -0.66
     thermique
    -0.64
    jsoup
    -0.62
    ]";
    -0.60
     restTemplate
    -0.60
    POSITIVE LOGITS
     potuto
    0.51
    lau
    0.47
    ChangeListener
    0.45
     cura
    0.45
    ধ
    0.45
    Locator
    0.45
    wad
    0.44
    초
    0.44
    mrow
    0.44
     Galla
    0.44
    Activations Density 2.891%

    No Known Activations