© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1810
    Prev
    Next
    INDEX
    Explanations

    It finds words relating to a person's willingness to take action, or words that express the speaker's opinion.

    oai_token-act-pair · gemini-2.0-flash

    do

    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
     nearly
    -3.05
    nearly
    -2.92
     Nearly
    -2.91
    Almost
    -2.83
     Almost
    -2.81
    Nearly
    -2.81
     almost
    -2.77
    almost
    -2.72
     virtually
    -2.31
     quase
    -2.25
    POSITIVE LOGITS
    featureID
    0.85
    AndEndTag
    0.73
     Normdatei
    0.66
    MLLoader
    0.64
    XMLSchema
    0.61
    談社
    0.59
     يتيمه
    0.58
    WaitGroup
    0.58
    новништво
    0.58
    mybatisplus
    0.57
    Activations Density 5.902%

    No Known Activations