© 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. 2994
    Prev
    Next
    INDEX
    Explanations

    text talking about preparing and serving pastries or desserts.

    oai_token-act-pair · 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
     bake
    -1.75
     Cake
    -1.63
     bakers
    -1.60
     baking
    -1.59
     baker
    -1.58
     cake
    -1.56
     Bake
    -1.56
    Cake
    -1.53
    Bake
    -1.53
     Baker
    -1.51
    POSITIVE LOGITS
    Renato
    0.46
     nonUne
    0.43
    ACIONES
    0.43
    reen
    0.43
     Александ
    0.43
     Selma
    0.43
     congenital
    0.43
    endregion
    0.43
    OLPH
    0.42
    laub
    0.42
    Activations Density 1.051%

    No Known Activations