© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12420
    Prev
    Next
    INDEX
    Explanations

    scientific text about copper sulfide nanoparticles

    oai_token-act-pair · gemini-2.0-flash

    x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Exactos
    -0.69
    UVWXYZ
    -0.63
    thâu
    -0.60
    ఔ
    -0.57
    Véxase
    -0.57
    ennia
    -0.56
    ברס
    -0.55
    SpringBootTest
    -0.55
     архивлан
    -0.54
    ocities
    -0.52
    POSITIVE LOGITS
     guest
    0.54
    Revenir
    0.52
    titleMargin
    0.51
    intas
    0.49
    RegressionTest
    0.49
    sneak
    0.49
     matic
    0.48
    guest
    0.47
    ]),
    0.47
     母
    0.46
    Activations Density 1.934%

    No Known Activations