© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4185
    Prev
    Next
    INDEX
    Explanations

    the word "content" and its related forms

    oai_token-act-pair · gemini-2.0-flash

    satisfaction or acceptance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    WEBPACK
    -0.85
    AddTagHelper
    -0.82
    prefixer
    -0.77
     насељу
    -0.76
    IUrlHelper
    -0.71
    Hochspringen
    -0.68
    '])){
    -0.67
    WriteAttribute
    -0.66
    AddAttribute
    -0.66
    Tembelea
    -0.66
    POSITIVE LOGITS
     contentment
    0.49
     satisfied
    0.48
     доволь
    0.48
     satisfaction
    0.45
    现状
    0.44
     satisfecho
    0.44
    Satisfaction
    0.43
     اکت
    0.43
     puas
    0.42
     lasciare
    0.42
    Activations Density 1.334%

    No Known Activations