© 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. 10751
    Prev
    Next
    INDEX
    Explanations

    phrases about observing or wanting to observe something

    oai_token-act-pair · gemini-2.0-flash

    see

    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
     see
    -0.50
     See
    -0.48
     seeing
    -0.46
     consulter
    -0.45
    dimethy
    -0.45
    見
    -0.45
     mostrarán
    -0.45
    adple
    -0.44
       
    -0.44
    见
    -0.43
    POSITIVE LOGITS
    ."</
    0.73
    )"),
    0.69
    saraba
    0.67
    UnsafeEnabled
    0.65
    tagHelperRunner
    0.64
     NSCoder
    0.62
    CompleteListener
    0.61
    yntaxException
    0.61
    onActivityResult
    0.61
    >";
    0.60
    Activations Density 7.536%

    No Known Activations