© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5296
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or gratitude

    oai_token-act-pair · gemini-2.0-flash

    expressions of excitement or enthusiasm

    np_token-act-pair-logits · gpt-4o-mini

    expressing surprise or gratitude

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    QMetaType
    -0.51
    ragment
    -0.47
     EconPapers
    -0.46
    ruptedException
    -0.45
    InMillis
    -0.44
     Ceremon
    -0.44
     Daya
    -0.44
     iprot
    -0.44
     testify
    -0.43
    lapsingToolbar
    -0.43
    POSITIVE LOGITS
     protoimpl
    0.66
    Begriffsklä
    0.65
    EndContext
    0.64
     تانيه
    0.61
    TintMode
    0.60
    تقاوى
    0.59
    ReusableCell
    0.59
    licet
    0.59
    Rhestr
    0.56
     CreateTagHelper
    0.56
    Activations Density 0.682%

    No Known Activations