© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11565
    Prev
    Next
    INDEX
    Explanations

    assignment operations in code and also the word "salt" specifically in recipes

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    sizeCache
    -0.89
    featureID
    -0.75
    CROSSTALK
    -0.71
    adaptiveStyles
    -0.70
    addCriterion
    -0.70
    oredCriteria
    -0.69
     a
    -0.69
     Réponses
    -0.68
     the
    -0.68
    StoreMessageInfo
    -0.67
    POSITIVE LOGITS
     ſche
    0.84
     auffi
    0.73
     ſy
    0.72
     houſe
    0.71
     iſt
    0.69
     photolibrary
    0.68
    ſelf
    0.67
     Jefus
    0.66
     Whigs
    0.65
    ſelves
    0.65
    Activations Density 0.559%

    No Known Activations