© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9147
    Prev
    Next
    INDEX
    Explanations

    passages describing immune responses, infection, or bacterial presence

    oai_token-act-pair · gemini-2.0-flash

    cooking

    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
     Bacterial
    -0.74
     bacterial
    -0.74
     fungal
    -0.65
     Microbial
    -0.60
     Bacteria
    -0.60
     microbial
    -0.59
     Viral
    -0.59
     Infected
    -0.58
    Bacterial
    -0.58
     TMPro
    -0.58
    POSITIVE LOGITS
     COOK
    1.29
     cook
    1.27
     Cook
    1.24
    Cook
    1.23
     cooking
    1.23
     chef
    1.16
     Cooking
    1.16
     cooks
    1.12
    cook
    1.12
    Cooking
    1.09
    Activations Density 3.088%

    No Known Activations