© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3776
    Prev
    Next
    INDEX
    Explanations

    a diverse mix of words, but with a particular emphasis on time, numbers, medical information, legal information, and scientific and technological information

    oai_token-act-pair · gemini-2.0-flash

    Past participles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Fe
    -0.50
    side
    -0.48
    fic
    -0.47
     mid
    -0.47
     Fe
    -0.47
    ati
    -0.47
     primary
    -0.46
     again
    -0.44
    ंदीखरीदारी
    -0.44
     counter
    -0.44
    POSITIVE LOGITS
    DockStyle
    0.91
    Vidite
    0.87
    RegressionTest
    0.78
     myſelf
    0.77
     doubtnut
    0.77
    abetes
    0.74
     समीक्षक
    0.73
     Monfieur
    0.73
    CloseOperation
    0.73
     Jefus
    0.72
    Activations Density 5.263%

    No Known Activations