© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8519
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to cooking, recipes, and ingredients

    oai_token-act-pair · gemini-2.0-flash

    non-English words or phrases

    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
    ArrowToggle
    -0.88
     Roskov
    -0.75
    PreferredItem
    -0.72
    IntoConstraints
    -0.65
    DebuggerNonUser
    -0.63
     dishes
    -0.57
    tagHelperRunner
    -0.57
    ⓧ
    -0.56
    MemoryWarning
    -0.55
    RegistryLite
    -0.54
    POSITIVE LOGITS
     neutre
    0.52
     yii
    0.52
     CreateTagHelper
    0.48
    andom
    0.48
    ありが
    0.48
    Autoritní
    0.47
    occasione
    0.47
     العملية
    0.46
    hermosa
    0.46
     Hivatalos
    0.46
    Activations Density 0.504%

    No Known Activations