© 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. 12437
    Prev
    Next
    INDEX
    Explanations

    mathematical problems phrased as questions (using comparative adjectives for values like largest, smallest, etc)

    oai_token-act-pair · gemini-2.0-flash

    superlatives and comparisons

    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
     largest
    -1.98
     longest
    -1.90
    largest
    -1.83
     strongest
    -1.80
     highest
    -1.78
     shortest
    -1.78
     fastest
    -1.76
     smallest
    -1.76
     greatest
    -1.73
     biggest
    -1.70
    POSITIVE LOGITS
     am
    0.61
    marginHorizontal
    0.45
    enha
    0.45
    pinMode
    0.44
    hdys
    0.44
    esgue
    0.43
    am
    0.43
    Am
    0.42
    Демографія
    0.42
     Torr
    0.42
    Activations Density 1.404%

    No Known Activations