© 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. 5355
    Prev
    Next
    INDEX
    Explanations

    ingredients one might find in a recipe

    oai_token-act-pair · gemini-2.0-flash

    culinary ingredients and flavors

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

    Recipes

    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
    гән
    -0.59
    ScopeManager
    -0.56
    Composable
    -0.54
    دری
    -0.50
    yntaxException
    -0.48
    FieldBuilder
    -0.48
     vực
    -0.47
    AccessorTable
    -0.47
    itário
    -0.47
    LEncoder
    -0.47
    POSITIVE LOGITS
     cherchés
    0.68
     Infórmanos
    0.64
    rungsseite
    0.58
     وتسجيلات
    0.56
     समीक्षाओं
    0.56
     flo
    0.54
     conos
    0.53
     CommonModule
    0.51
    Ծանոթ
    0.51
     layui
    0.49
    Activations Density 0.741%

    No Known Activations