© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16192
    Prev
    Next
    INDEX
    Explanations

    words or phrases expressing positive sentiment

    oai_token-act-pair · gemini-2.0-flash

    positive emotions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     propOrder
    -0.56
     juridique
    -0.50
     scolaires
    -0.50
     Monfieur
    -0.48
    RectangleBorder
    -0.47
     BoxDecoration
    -0.47
    asnya
    -0.47
     régionales
    -0.47
     disant
    -0.47
     masculinos
    -0.47
    POSITIVE LOGITS
     nostalgia
    0.78
     excitement
    0.74
     happiness
    0.64
     tranquility
    0.60
     adventure
    0.59
     escap
    0.59
     joy
    0.59
     simplicity
    0.59
     anticipation
    0.58
     laughter
    0.57
    Activations Density 5.069%

    No Known Activations