© 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. 12546
    Prev
    Next
    INDEX
    Explanations

    information about authors of scientific papers, copyright notices, email addresses, and phone numbers

    oai_token-act-pair · 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
     Per
    -0.48
     #
    -0.45
     P
    -0.42
     K
    -0.41
     cobre
    -0.40
    our
    -0.40
    ैल
    -0.40
     never
    -0.40
     basic
    -0.40
     per
    -0.39
    POSITIVE LOGITS
     itſelf
    0.78
    ^(@)
    0.76
     $_"
    0.74
    DebuggerNonUser
    0.71
     TableColumn
    0.68
     metav
    0.68
     myſelf
    0.68
     Theſe
    0.68
     MessageBoxIcon
    0.68
    InjectAttribute
    0.67
    Activations Density 1.424%

    No Known Activations