© 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. 13269
    Prev
    Next
    INDEX
    Explanations

    the syllable "Tre" within words

    oai_token-act-pair · gemini-2.0-flash

    Tre

    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
    ContentAsync
    -0.78
    WSGI
    -0.73
     tartalomajánló
    -0.72
    soever
    -0.68
    Hentet
    -0.66
    (!__
    -0.65
     Wikimedijinoj
    -0.63
     iconLine
    -0.63
    writeField
    -0.63
    DataAnnotations
    -0.62
    POSITIVE LOGITS
    PhysRevLett
    0.44
    المكان
    0.42
    qual
    0.40
     qual
    0.40
    unlink
    0.40
    banan
    0.40
    上げた
    0.40
     kaynağından
    0.39
    държа
    0.39
    ühnen
    0.39
    Activations Density 0.471%

    No Known Activations