© 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. 8100
    Prev
    Next
    INDEX
    Explanations

    punctuation paired with context words

    oai_token-act-pair · gemini-2.0-flash

    ,

    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
    .
    -0.89
     .
    -0.84
    1
    -0.79
     :
    -0.76
    <eos>
    -0.76
    2
    -0.76
      
    -0.75
    :
    -0.74
    ;
    -0.74
     ;
    -0.74
    POSITIVE LOGITS
     Efq
    1.72
     avoient
    1.68
     myſelf
    1.66
     fermés
    1.62
     démocr
    1.61
     feroit
    1.60
     scolaires
    1.58
     sauvages
    1.56
     ProtoMessage
    1.55
     chré
    1.55
    Activations Density 12.642%

    No Known Activations