© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11298
    Prev
    Next
    INDEX
    Explanations

    seemingly random junk tokens that separate sections, appear to represent formatting artifacts in the text

    oai_token-act-pair · gemini-2.0-flash

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ngdoc
    -0.75
    ylvan
    -0.54
    InSection
    -0.50
    下载附件
    -0.50
     protoimpl
    -0.48
    itschrift
    -0.48
    aspectj
    -0.47
     initComponents
    -0.47
     ори
    -0.47
    feier
    -0.47
    POSITIVE LOGITS
    ]));
    0.63
    ("")]
    0.60
     незавершена
    0.54
    новништво
    0.54
    }}]{
    0.54
    )";
    0.53
     itſelf
    0.52
    )}]{
    0.51
    — 
    0.51
    dymyr
    0.51
    Activations Density 0.679%

    No Known Activations