Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10382
    Prev
    Next
    INDEX
    Explanations

    recipes involving potatoes

    oai_token-act-pair · gemini-2.0-flash

    potato

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    Życiorys
    -0.53
     contas
    -0.50
    liosis
    -0.48
    Racism
    -0.48
     operação
    -0.47
     createSprite
    -0.46
     Méditerranée
    -0.46
    encodeWith
    -0.46
     ioutil
    -0.45
    SWIG
    -0.45
    POSITIVE LOGITS
     potatoes
    0.95
     potato
    0.94
     Potato
    0.85
    potato
    0.82
     Potatoes
    0.81
    Potato
    0.77
    Potatoes
    0.75
     starch
    0.74
     mashed
    0.74
     Kartoffeln
    0.69
    Activations Density 0.666%

    No Known Activations