© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13666
    Prev
    Next
    INDEX
    Explanations

    the fragment "Ad" possibly as an abbreviation

    oai_token-act-pair · gemini-2.0-flash

    Ad

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     AssemblyTitle
    -0.84
    ItemBackground
    -0.74
     jsPsych
    -0.73
     CreateTagHelper
    -0.73
    WriteTagHelper
    -0.67
    endphp
    -0.67
    AsUp
    -0.65
    AccessorTable
    -0.62
    HasAnnotation
    -0.60
    AddTagHelper
    -0.60
    POSITIVE LOGITS
    hey
    0.41
    alth
    0.39
    kraut
    0.36
    jat
    0.35
    vera
    0.34
     NET
    0.34
    ложение
    0.34
    pan
    0.34
    alt
    0.34
    ar
    0.34
    Activations Density 1.339%

    No Known Activations