© 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. 13224
    Prev
    Next
    INDEX
    Explanations

    legal and financial documents.

    oai_token-act-pair · gemini-2.0-flash

    Court

    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
    rungsseite
    -0.82
     NSCoder
    -0.79
    RegressionTest
    -0.78
     kasarigan
    -0.76
    IntoConstraints
    -0.75
     CreateTagHelper
    -0.73
    cyklopedia
    -0.72
     <=",
    -0.71
    IVEREF
    -0.71
    DeleteBehavior
    -0.69
    POSITIVE LOGITS
    topus
    0.41
    PreAuthorize
    0.40
    обеди
    0.39
     information
    0.39
    opel
    0.38
    CDU
    0.37
    vő
    0.37
    mogelijk
    0.37
     saks
    0.36
    样
    0.36
    Activations Density 0.646%

    No Known Activations