© 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. 10453
    Prev
    Next
    INDEX
    Explanations

    code snippets, potentially equations and/or file paths, and numbers

    oai_token-act-pair · gemini-2.0-flash

    code and numbers

    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
    ViewFeatures
    -0.99
    endphp
    -0.97
    WebVitals
    -0.93
    sidemargin
    -0.90
    +#+#
    -0.89
    الحياه
    -0.88
    bootstrapcdn
    -0.88
    ArgsConstructor
    -0.87
    PerformLayout
    -0.83
    AddTagHelper
    -0.83
    POSITIVE LOGITS
     activated
    0.47
    Vis
    0.46
     multiple
    0.45
     Ex
    0.45
     Multiple
    0.44
     Vis
    0.42
    pl
    0.42
    sp
    0.42
     referenties
    0.41
     visualisation
    0.41
    Activations Density 6.328%

    No Known Activations