© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14602
    Prev
    Next
    INDEX
    Explanations

    words and phrases that add nuance or a degree of uncertainty to a claim.

    oai_token-act-pair · gemini-2.0-flash

    abstract concepts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    +#+#
    -0.98
     '\\;'
    -0.82
     démocratie
    -0.80
     bonté
    -0.75
     colère
    -0.75
     nahilalakip
    -0.73
     sagesse
    -0.71
     dignité
    -0.70
     république
    -0.69
     veille
    -0.67
    POSITIVE LOGITS
     situation
    1.11
     mixture
    1.03
     idea
    0.96
     combination
    0.95
     solution
    0.94
     approach
    0.92
     framework
    0.90
     timeframe
    0.90
     scheme
    0.90
     concept
    0.89
    Activations Density 10.196%

    No Known Activations