© 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. 14977
    Prev
    Next
    INDEX
    Explanations

    labels within scientific papers as well as years and people in the papers.

    oai_token-act-pair · gemini-2.0-flash

    also

    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
    ătate
    -0.44
    ling
    -0.43
    épendance
    -0.42
    himovic
    -0.42
    onPressed
    -0.42
    Karriere
    -0.42
    ity
    -0.42
    OrBuilder
    -0.41
     wherever
    -0.40
    ork
    -0.40
    POSITIVE LOGITS
     also
    2.23
     Also
    2.06
    also
    2.03
    Also
    2.03
     también
    1.75
     também
    1.74
     ALSO
    1.70
     også
    1.65
    también
    1.59
     также
    1.50
    Activations Density 1.422%

    No Known Activations