© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5970
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation, specifically identifying file paths, API mentions, and references to academic institutions, especially those in China, and the regions 'US', 'en'

    oai_token-act-pair · gemini-2.0-flash

    us

    np_max-act · gemini-2.0-flash

    us

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    AutoScaleMode
    -1.02
    GEBURTSDATUM
    -1.02
     betweenstory
    -0.93
    afficheront
    -0.92
     виправивши
    -0.90
    contentLoaded
    -0.90
    queryInterface
    -0.86
    berdayakan
    -0.83
    abestanden
    -0.83
    +#+#
    -0.83
    POSITIVE LOGITS
    ud
    0.43
    );
    0.43
     ex
    0.42
     special
    0.41
    fe
    0.40
     meg
    0.40
    )?
    0.39
     example
    0.39
     
    0.39
     ihr
    0.38
    Activations Density 2.633%

    No Known Activations