© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11470
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating positive encouragement or influence, particularly in educational contexts

    oai_token-act-pair · 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
    !*\
    -0.69
     الرياضيه
    -0.65
     szóci
    -0.60
     pleaſure
    -0.59
     Grecs
    -0.59
     majeurs
    -0.59
    BagLayout
    -0.57
    /*
    -0.57
     végétale
    -0.56
    KommentareTeilen
    -0.56
    POSITIVE LOGITS
    SBATCH
    0.66
     G
    0.48
    DispatchToProps
    0.47
    NameInMap
    0.47
    opted
    0.47
    reso
    0.45
    craft
    0.45
    carried
    0.44
    attractive
    0.44
    dumb
    0.44
    Activations Density 2.903%

    No Known Activations