© 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. 10526
    Prev
    Next
    INDEX
    Explanations

    terms used in scientific experiments

    oai_token-act-pair · gemini-2.0-flash

    scientific processes

    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
    Facades
    -0.43
    蹟
    -0.43
    ImageIO
    -0.42
     Reach
    -0.40
     stanovnika
    -0.39
    を経て
    -0.38
     doInBackground
    -0.38
    <bos>
    -0.38
    windowFixed
    -0.37
    reach
    -0.36
    POSITIVE LOGITS
    aarrggbb
    0.82
     itſelf
    0.74
     Grecs
    0.71
     transfieras
    0.68
     dieux
    0.65
     preſent
    0.65
     myſelf
    0.65
    disfraz
    0.64
     ſtate
    0.64
     enfans
    0.63
    Activations Density 5.250%

    No Known Activations