© 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. 5986
    Prev
    Next
    INDEX
    Explanations

    various discourse markers and conjunctions, particularly those expressing surprise, continuation, or mild disagreement.

    oai_token-act-pair · gemini-2.0-flash

    Expressing surprise

    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
     myſelf
    -0.69
     للمعارف
    -0.68
    abestanden
    -0.66
    ^(@)
    -0.65
     Trouver
    -0.64
     unknownFields
    -0.64
     BoxFit
    -0.62
    )\}$
    -0.60
    リューション
    -0.59
    \]
    -0.57
    POSITIVE LOGITS
     boy
    1.63
     oh
    1.59
     wow
    1.49
     Oh
    1.45
    Oh
    1.41
     Wow
    1.32
    wow
    1.30
    Wow
    1.30
    boy
    1.29
     WOW
    1.27
    Activations Density 0.786%

    No Known Activations