© 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. 6321
    Prev
    Next
    INDEX
    Explanations

    the word "happy"

    oai_token-act-pair · gemini-2.0-flash

    happy

    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
     disambiguazione
    -1.38
     unknownFields
    -1.36
    Portale
    -1.31
     Мексичка
    -1.29
    DockStyle
    -1.28
    ChildScrollView
    -1.25
    extAlignment
    -1.25
    parsedMessage
    -1.24
    Portály
    -1.23
    IUrlHelper
    -1.23
    POSITIVE LOGITS
    The
    1.11
     
    1.11
    ↵↵
    0.98
    o
    0.93
    <strong>
    0.91
    2
    0.90
    1
    0.90
    3
    0.89
    a
    0.87
    0.86
    Activations Density 1.064%
    No Known Activations