© 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. 14486
    Prev
    Next
    INDEX
    Explanations

    words related to fine particles, solutions, and fertilizer chemicals

    oai_token-act-pair · gemini-2.0-flash

    Powders

    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
     Powder
    -1.62
     powder
    -1.58
    Powder
    -1.51
    powder
    -1.38
     powders
    -1.30
     powdered
    -1.29
     powdery
    -1.18
     polvo
    -1.09
     Dust
    -1.01
     dust
    -0.99
    POSITIVE LOGITS
    AndroidJUnit
    0.61
    ographia
    0.56
    KommentareTeilen
    0.53
    ConstraintMaker
    0.52
    OLIS
    0.50
    kháu
    0.50
    TagMode
    0.49
    mbic
    0.48
    ={({
    0.47
    новниш
    0.47
    Activations Density 3.715%

    No Known Activations