© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4819
    Prev
    Next
    INDEX
    Explanations

    phrases containing the words "you" and "need", especially when discussing delivery.

    oai_token-act-pair · gemini-2.0-flash

    emergency

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    Geplaatst
    -0.89
     kasarigan
    -0.87
     autorytatywna
    -0.81
    Rhestr
    -0.80
     متعلقه
    -0.79
     propOrder
    -0.76
     Shakspeare
    -0.75
    fjspx
    -0.72
     EconPapers
    -0.71
    ſelves
    -0.71
    POSITIVE LOGITS
     emergency
    1.89
    emergency
    1.61
    Emergency
    1.55
     Emergency
    1.54
     emergencies
    1.48
     EMERGENCY
    1.48
     urgent
    1.46
     urgency
    1.41
    EMERGENCY
    1.33
     emergencia
    1.25
    Activations Density 0.707%

    No Known Activations