© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3464
    Prev
    Next
    INDEX
    Explanations

    descriptions of items for sale

    oai_token-act-pair · gemini-2.0-flash

    new

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    HtmlAttribute
    -0.67
    Geplaatst
    -0.66
     doInBackground
    -0.65
    __':
    -0.65
     &___
    -0.65
    tagext
    -0.64
     transférez
    -0.63
    achella
    -0.61
     WaitForSeconds
    -0.60
    Datuak
    -0.60
    POSITIVE LOGITS
     new
    2.94
    new
    2.59
     nuevas
    1.95
     nuevos
    1.95
     nueva
    1.93
     nuovi
    1.84
     neuen
    1.83
     novos
    1.83
     nuevo
    1.82
     neue
    1.82
    Activations Density 2.235%

    No Known Activations