© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2875
    Prev
    Next
    INDEX
    Explanations

    food ingredient names

    oai_token-act-pair · gemini-2.0-flash

    food ingredients/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_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
     snippetHide
    -0.50
    ILayout
    -0.41
    complexContent
    -0.41
     si
    -0.39
     sub
    -0.39
     mo
    -0.38
     CURLOPT
    -0.38
     fi
    -0.38
    ')}}">
    -0.37
    nextProps
    -0.36
    POSITIVE LOGITS
     الحره
    0.96
    aarrggbb
    0.80
    Demikian
    0.80
     Савезне
    0.77
    IsMutable
    0.77
     autorytatywna
    0.74
     HasFactory
    0.73
    MigrationBuilder
    0.73
    Демографія
    0.71
    Datuak
    0.70
    Activations Density 1.434%

    No Known Activations