© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2740
    Prev
    Next
    INDEX
    Explanations

    sentences describing daily activities

    oai_token-act-pair · gemini-2.0-flash

    activities related to outdoor recreation

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

    hobbies and activities

    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
     henvisninger
    -0.49
    DispatchToProps
    -0.48
     Chosen
    -0.45
     sapat
    -0.45
    akujem
    -0.45
     leben
    -0.44
     Capit
    -0.43
     IERC
    -0.42
    Chosen
    -0.42
    今回は
    -0.42
    POSITIVE LOGITS
     مرئيه
    0.67
    WithIOException
    0.65
    RegressionTest
    0.65
     cooking
    0.63
    =$?
    0.60
    cooking
    0.60
    LLocation
    0.58
     Hiking
    0.57
     hiking
    0.57
    atrième
    0.57
    Activations Density 3.392%

    No Known Activations