© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11472
    Prev
    Next
    INDEX
    Explanations

    a mix of Japanese technical words, internet URLs, and references to date/time formats in code

    oai_token-act-pair · gemini-2.0-flash

    scientific research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    int
    -0.60
    om
    -0.58
     iconFacebook
    -0.58
    un
    -0.58
    he
    -0.58
    iz
    -0.58
    ate
    -0.57
    st
    -0.57
    as
    -0.57
    if
    -0.56
    POSITIVE LOGITS
     igång
    0.63
     stället
    0.57
     feroit
    0.54
     regeringen
    0.52
     tänka
    0.52
    
    0.52
     öppna
    0.50
     prisonniers
    0.49
     mères
    0.49
     ouvriers
    0.48
    Activations Density 1.981%

    No Known Activations