© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10705
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with working on or debugging a computer.

    oai_token-act-pair · gemini-2.0-flash

    French pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     d
    -0.50
     Ext
    -0.48
     mo
    -0.47
     Des
    -0.47
    хьтан
    -0.47
    dics
    -0.46
    quo
    -0.46
    eur
    -0.45
    Scroller
    -0.45
    dez
    -0.45
    POSITIVE LOGITS
     étoient
    0.77
     avoient
    0.77
     étoit
    0.76
     auroit
    0.71
     pouvoit
    0.69
     feroit
    0.68
     resourceCulture
    0.68
     vectorielles
    0.65
    PreferredItem
    0.63
     quæ
    0.62
    Activations Density 1.381%

    No Known Activations