© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2571
    Prev
    Next
    INDEX
    Explanations

    words related to attending, participating, and enjoying events, activities, or studies

    oai_token-act-pair · gemini-2.0-flash

    attend

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     attend
    -2.28
     attended
    -2.08
     attending
    -2.06
     Attend
    -2.00
     attends
    -1.99
     attendance
    -1.88
    Attend
    -1.86
     Attending
    -1.86
    attend
    -1.81
    attended
    -1.73
    POSITIVE LOGITS
    ScopeManager
    0.60
     GetComponent
    0.56
    NewLabel
    0.55
     OnTriggerEnter
    0.55
    igration
    0.55
     numerus
    0.55
     Frente
    0.53
    TestingModule
    0.52
    NavController
    0.52
    raulic
    0.49
    Activations Density 7.405%

    No Known Activations