© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13453
    Prev
    Next
    INDEX
    Explanations

    words related to enthusiasm or dedication

    oai_token-act-pair · gemini-2.0-flash

    passion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    IndentedString
    -0.81
     snippetHide
    -0.81
    GEBURTSDATUM
    -0.80
     astore
    -0.76
     resourceCulture
    -0.76
    AndEndTag
    -0.72
     AssemblyProduct
    -0.71
     pleaſure
    -0.69
    .*")]
    -0.68
    CppMethod
    -0.68
    POSITIVE LOGITS
     about
    0.49
     to
    0.46
    wts
    0.46
     renda
    0.46
    ️
    0.44
    about
    0.43
     hồ
    0.42
    utuhan
    0.41
    auré
    0.40
    cedido
    0.40
    Activations Density 1.761%

    No Known Activations