© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 4494
    Prev
    Next
    INDEX
    Explanations

    positive sentiment in customer reviews, especially towards creative or bespoke products.

    oai_token-act-pair · gemini-2.0-flash

    positive sentiments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    OGND
    -0.88
     cute
    -0.83
     sweetest
    -0.82
     cutest
    -0.78
     handsome
    -0.77
     adorable
    -0.77
     brilliant
    -0.76
    Lovely
    -0.76
    Cute
    -0.76
    Brilliant
    -0.75
    POSITIVE LOGITS
     drop
    0.72
     breath
    0.71
     absolutely
    0.62
     be
    0.62
    drop
    0.60
     Drop
    0.58
    makeText
    0.58
    Drop
    0.57
     breathe
    0.56
    Breath
    0.56
    Activations Density 1.317%

    No Known Activations