© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13504
    Prev
    Next
    INDEX
    Explanations

    words associated with research collaboration and cultural preservation

    oai_token-act-pair · gemini-2.0-flash

    terms associated with cooperation and collaboration in research

    np_token-act-pair-logits · gpt-4o-mini

    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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ***!
    -0.52
    tikum
    -0.49
    TAA
    -0.48
     aéreo
    -0.47
    oprot
    -0.47
     tặng
    -0.45
    uttu
    -0.44
    AnchorStyles
    -0.44
    astéroïdes
    -0.43
    wiada
    -0.43
    POSITIVE LOGITS
    rungsseite
    0.73
    GraphicsUnit
    0.63
    Aktualisiert
    0.57
    atine
    0.56
     MyBatis
    0.56
     propOrder
    0.56
    ricus
    0.54
    WithIOException
    0.54
    ритори
    0.53
    Personendaten
    0.52
    Activations Density 1.037%

    No Known Activations