© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7284
    Prev
    Next
    INDEX
    Explanations

    sentences about feeling surprised about something

    oai_token-act-pair · gemini-2.0-flash

    surprised

    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
     EconPapers
    -0.57
    Insee
    -0.50
    PreferredItem
    -0.49
    getMenuInflater
    -0.48
    شهاد
    -0.48
     CreateTagHelper
    -0.47
     webbplats
    -0.47
     сожалению
    -0.46
    btnut
    -0.46
     препратки
    -0.45
    POSITIVE LOGITS
    Lähteet
    0.65
    }));
    0.55
    rceil
    0.54
     '\\;'
    0.54
    OGND
    0.53
     justa
    0.52
    PerformLayout
    0.51
    fcntl
    0.50
     beholder
    0.50
     debout
    0.49
    Activations Density 3.485%

    No Known Activations