© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2449
    Prev
    Next
    INDEX
    Explanations

    phrases containing numerical quantifiers like "a number of", "several", "more", or "some"

    oai_token-act-pair · gemini-2.0-flash

    of or several

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     ſeveral
    -1.40
     feveral
    -1.20
     myſelf
    -1.20
     Theſe
    -1.19
     itſelf
    -1.19
     doubtnut
    -1.16
     photolibrary
    -1.12
     Efq
    -1.10
    []
    -1.09
     houſe
    -1.09
    POSITIVE LOGITS
    ↵
    0.61
     really
    0.60
    ↵↵
    0.59
         
    0.58
      
    0.58
    <eos>
    0.57
     of
    0.57
    0.57
        
    0.56
            
    0.56
    Activations Density 3.464%

    No Known Activations