© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5232
    Prev
    Next
    INDEX
    Explanations

    phrases related to weather, disasters, and sports events that lead to delays

    oai_token-act-pair · gemini-2.0-flash

    Negative events

    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
    ConstraintMaker
    -0.76
    principalTable
    -0.68
     Seeder
    -0.64
     nahilalakip
    -0.61
     onAnimation
    -0.58
    homonymie
    -0.57
     يتيمه
    -0.57
    webElementXpaths
    -0.56
    RequestOptions
    -0.56
     HasFactory
    -0.55
    POSITIVE LOGITS
    par
    0.57
     Normdatei
    0.56
     parag
    0.55
    takan
    0.52
     ModelExpression
    0.50
     ImGui
    0.48
    apar
    0.47
     par
    0.47
     Chwiliwch
    0.47
     fosfor
    0.47
    Activations Density 2.962%

    No Known Activations