© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3726
    Prev
    Next
    INDEX
    Explanations

    technical jargon from a wide variety of scientific fields

    oai_token-act-pair · gemini-2.0-flash

    technical descriptions

    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
    You
    -0.45
    ApiModelProperty
    -0.44
    ఔ
    -0.41
     Nós
    -0.40
     Soyez
    -0.39
    vening
    -0.38
    Escolha
    -0.38
    kleidung
    -0.37
     You
    -0.37
    This
    -0.37
    POSITIVE LOGITS
     In
    1.54
    In
    1.23
     On
    1.09
     As
    1.07
     Of
    1.05
     At
    0.99
    Of
    0.98
     Into
    0.94
     Within
    0.88
    As
    0.87
    Activations Density 25.935%

    No Known Activations