© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3710
    Prev
    Next
    INDEX
    Explanations

    adverbs and subjective adjectives related to feelings or opinions

    oai_token-act-pair · gemini-2.0-flash

    Uncertainty/explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ContentAsync
    -0.85
    
    -0.79
     مشين
    -0.75
    RenderAtEndOf
    -0.74
    存于互联网档案馆
    -0.70
     contextLoads
    -0.68
    AddTagHelper
    -0.68
    StoryboardSegue
    -0.66
    WriteLiteral
    -0.66
     beginnetje
    -0.66
    POSITIVE LOGITS
     other
    0.52
     then
    0.50
     promptly
    0.44
     frappé
    0.44
     held
    0.43
     earth
    0.43
     sat
    0.42
    then
    0.42
     never
    0.41
    ฏ
    0.41
    Activations Density 3.708%

    No Known Activations