© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10302
    Prev
    Next
    INDEX
    Explanations

    content about chocolate chip cookies and thermistors

    oai_token-act-pair · gemini-2.0-flash

    Desserts and sweet foods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     AssemblyCompany
    -0.69
     betweenstory
    -0.69
     vPvB
    -0.66
    Portail
    -0.65
    argout
    -0.62
    
    -0.62
    rrggbb
    -0.60
    sizeCache
    -0.60
     PX
    -0.60
    guenos
    -0.60
    POSITIVE LOGITS
    ũng
    0.44
     salads
    0.44
     réfrigérateur
    0.43
    ::::::::
    0.42
     creams
    0.40
     Cakes
    0.40
    ertas
    0.40
    thday
    0.39
     tä
    0.39
     Cupcakes
    0.38
    Activations Density 7.926%

    No Known Activations