© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2684
    Prev
    Next
    INDEX
    Explanations

    words related to events, like battles, travels, stories, and celebrations

    oai_token-act-pair · gemini-2.0-flash

    actions and events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    principalColumn
    -0.72
    setVerticalGroup
    -0.65
    WireFormatLite
    -0.64
    InjectAttribute
    -0.60
     Chwiliwch
    -0.59
     isInitialized
    -0.58
    forName
    -0.58
    sizeCache
    -0.56
     незавершена
    -0.56
     szóci
    -0.55
    POSITIVE LOGITS
     كومونز
    0.58
    .*")]
    0.50
    worten
    0.48
     noten
    0.46
    tarea
    0.46
    گاب
    0.46
    aboo
    0.45
    thritis
    0.45
    apura
    0.44
     CURIAM
    0.43
    Activations Density 45.194%

    No Known Activations