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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6420
    Prev
    Next
    INDEX
    Explanations

    words related to weather, especially rain and snow with modifying techniques

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "fall"

    np_token-act-pair-logits · gpt-4o-mini

    fall

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     burner
    -0.49
    AddTagHelper
    -0.49
    StoredProcedure
    -0.48
    ervis
    -0.47
    ublic
    -0.46
    SequentialGroup
    -0.44
    AsUp
    -0.43
     getChild
    -0.42
    Vec
    -0.42
     Vec
    -0.42
    POSITIVE LOGITS
     fall
    2.09
     falling
    2.02
     falls
    1.94
     fell
    1.84
    fall
    1.75
     Fall
    1.71
     fallen
    1.70
     Falling
    1.69
    Fall
    1.65
    falling
    1.62
    Activations Density 1.102%

    No Known Activations