© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8085
    Prev
    Next
    INDEX
    Explanations

    statistical summaries, especially those including "estimator", "reduction", and "coverage"

    oai_token-act-pair · gemini-2.0-flash

    everywhere

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     Roskov
    -0.90
     tartalomajánló
    -0.66
    SequentialGroup
    -0.64
    íncia
    -0.59
     الدولى
    -0.57
    initializeApp
    -0.56
    AddressBook
    -0.55
    topt
    -0.55
     通販
    -0.54
    يكب
    -0.54
    POSITIVE LOGITS
     everywhere
    0.92
     partout
    0.77
     Everywhere
    0.76
    everywhere
    0.74
     בכל
    0.69
    ทุก
    0.69
     wherever
    0.68
    Everywhere
    0.67
     for
    0.66
     whenever
    0.66
    Activations Density 2.946%

    No Known Activations