© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12457
    Prev
    Next
    INDEX
    Explanations

    mentions of chefs, particularly in the context of the White House.

    oai_token-act-pair · gemini-2.0-flash

    references to chefs and cooking in a formal context

    np_token-act-pair-logits · gpt-4o-mini

    Chefs and restaurants

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     فريبيس
    -0.68
    TagHelper
    -0.56
    enderror
    -0.54
    Gambas
    -0.52
    Билгалдахарш
    -0.51
     intptr
    -0.51
    adpleegd
    -0.50
    afi
    -0.49
     dépend
    -0.48
    Према
    -0.48
    POSITIVE LOGITS
     مرئيه
    0.69
    SequentialGroup
    0.61
     CreateTagHelper
    0.53
    iele
    0.52
    RectangleBorder
    0.50
    úde
    0.47
    ondere
    0.47
     propertyName
    0.47
    inguish
    0.47
     puissiez
    0.46
    Activations Density 1.022%

    No Known Activations