© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9591
    Prev
    Next
    INDEX
    Explanations

    words describing tools, objectives and methods for scientific investigation and analysis

    oai_token-act-pair · gemini-2.0-flash

    scientific imaging analysis

    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
    camb
    -0.43
     guns
    -0.38
    ո
    -0.36
     completed
    -0.35
     task
    -0.35
    wps
    -0.35
    PACE
    -0.35
     complete
    -0.35
     to
    -0.35
    addCriterion
    -0.34
    POSITIVE LOGITS
     intptr
    0.82
     Italijanski
    0.80
    dafx
    0.79
    Abit
    0.75
     pinulongan
    0.74
    ScopeManager
    0.71
     passés
    0.71
     Leeuwen
    0.68
    hésite
    0.68
     AssemblyVersion
    0.68
    Activations Density 1.232%

    No Known Activations