© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11021
    Prev
    Next
    INDEX
    Explanations

    common words such as "to," "will," "or" and pronouns such as "we", "it", "they" when these are alongside other words in sentences

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Cour
    -0.60
    astéroïdes
    -0.59
    localctx
    -0.59
    كويكب
    -0.57
    ItemBackground
    -0.57
    omock
    -0.55
    cyklopedia
    -0.55
    ArrowToggle
    -0.48
    xnn
    -0.48
    ولوجيا
    -0.47
    POSITIVE LOGITS
    
    0.93
     nakalista
    0.75
     '\\;'
    0.69
    endphp
    0.66
    PageContext
    0.63
     file
    0.60
    outWeight
    0.55
     فريبيس
    0.54
    WriteBarrier
    0.54
     FILE
    0.54
    Activations Density 5.224%

    No Known Activations