© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6466
    Prev
    Next
    INDEX
    Explanations

    words related to the Spanish language, computer programming, and Italian place names

    oai_token-act-pair · gemini-2.0-flash

    del

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     del
    -2.25
     DEL
    -1.65
     Del
    -1.59
    Del
    -1.58
    del
    -1.51
    DEL
    -1.41
     dell
    -1.15
     dele
    -0.99
     della
    -0.93
     deli
    -0.90
    POSITIVE LOGITS
     of
    0.83
     stør
    0.83
    <bos>
    0.78
     bekym
    0.69
     nyug
    0.68
     kroppen
    0.63
     vroe
    0.61
     hvit
    0.60
     høy
    0.60
    of
    0.60
    Activations Density 0.139%

    No Known Activations