© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12605
    Prev
    Next
    INDEX
    Explanations

    words that describe importance or high degree

    oai_token-act-pair · gemini-2.0-flash

    prefixes/degree

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    complexContent
    -0.89
    MemoryWarning
    -0.84
     EconPapers
    -0.83
     referenties
    -0.79
    RetentionPolicy
    -0.76
    TemporalType
    -0.73
     Himo
    -0.72
    ttino
    -0.72
     محفوظة
    -0.72
     дописавши
    -0.71
    POSITIVE LOGITS
    lus
    0.44
     tre
    0.42
     of
    0.41
    mappedBy
    0.41
    ctile
    0.41
     Ver
    0.40
    ENBERG
    0.39
    лене
    0.39
    RunAsync
    0.39
     online
    0.38
    Activations Density 2.147%

    No Known Activations