© 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. 15126
    Prev
    Next
    INDEX
    Explanations

    words or phrases which denote a sentence break, change of subject, or emotional reaction

    oai_token-act-pair · gemini-2.0-flash

    periods

    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
     vi
    -0.45
     du
    -0.44
     sur
    -0.43
    "
    -0.41
     Gras
    -0.40
    â
    -0.39
     per
    -0.39
    Il
    -0.39
    es
    -0.38
    ・・・
    -0.38
    POSITIVE LOGITS
    ThroughAttribute
    0.99
    AccessorTable
    0.93
    TintMode
    0.93
    yntaxException
    0.91
    Personendaten
    0.91
    WriteBarrier
    0.88
    Autoritní
    0.86
    ]")]
    0.85
    LookAnd
    0.81
    WireFormatLite
    0.80
    Activations Density 2.301%

    No Known Activations