© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11576
    Prev
    Next
    INDEX
    Explanations

    statistical analyses of scientific study results

    oai_token-act-pair · gemini-2.0-flash

    could

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    Personensuche
    -1.01
    parsedMessage
    -0.98
    AccessorTable
    -0.97
     nahilalakip
    -0.94
    Personendaten
    -0.93
    tvguidetime
    -0.88
    aarrggbb
    -0.86
    featureID
    -0.83
    WriteTagHelper
    -0.83
    الإنجليزية
    -0.80
    POSITIVE LOGITS
     could
    2.20
    could
    1.87
     Could
    1.79
    Could
    1.73
     COULD
    1.48
     couldn
    1.06
     kunne
    1.02
     kunde
    0.94
     poderia
    0.94
     podría
    0.93
    Activations Density 2.217%

    No Known Activations