© 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
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14699
    Prev
    Next
    INDEX
    Explanations

    language expressing endearment or strong emotion

    oai_token-act-pair · gemini-2.0-flash

    Affection and emotion

    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
    RectangleBorder
    -0.65
     Wern
    -0.63
     متحده
    -0.61
     eun
    -0.57
     esters
    -0.56
     pyrite
    -0.55
     Wissenschaften
    -0.55
     Thermodynamics
    -0.54
    InjectMocks
    -0.53
    erevan
    -0.53
    POSITIVE LOGITS
    ✨:
    0.55
     papers
    0.49
     ostavi
    0.49
     CoreData
    0.48
     iconLine
    0.48
    цезда
    0.47
    potamus
    0.47
    зулта
    0.46
    -------------</
    0.46
    haviours
    0.46
    Activations Density 0.924%

    No Known Activations