© 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. 5412
    Prev
    Next
    INDEX
    Explanations

    statements showing appreciation for another person's work or opinion.

    oai_token-act-pair · gemini-2.0-flash

    addressing a group

    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
     they
    -0.72
     juos
    -0.67
     They
    -0.67
    They
    -0.60
    mereka
    -0.60
     őket
    -0.59
    你的
    -0.57
     iyong
    -0.56
     natin
    -0.56
     atve
    -0.55
    POSITIVE LOGITS
     guys
    1.34
    Guys
    1.11
    guys
    1.09
     yall
    1.02
     GUYS
    0.98
     Guys
    0.97
     gentlemen
    0.86
     folks
    0.85
    Gentlemen
    0.83
     lads
    0.82
    Activations Density 1.161%

    No Known Activations