© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9942
    Prev
    Next
    INDEX
    Explanations

    text mentioning research or studies

    oai_token-act-pair · gemini-2.0-flash

    research

    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
     research
    -1.09
    research
    -1.01
     Research
    -0.94
     RESEARCH
    -0.90
    Research
    -0.88
     researches
    -0.87
     researcher
    -0.84
     studies
    -0.80
    RESEARCH
    -0.79
     investigation
    -0.78
    POSITIVE LOGITS
    stateProvider
    0.59
    faccia
    0.57
    ometal
    0.54
     scolas
    0.50
    dbname
    0.48
     Batal
    0.48
    quadratic
    0.48
     puissiez
    0.47
     Classical
    0.47
     fermions
    0.47
    Activations Density 10.526%

    No Known Activations