© 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. 3858
    Prev
    Next
    INDEX
    Explanations

    capitalized words that might represent names, locations, or trademarks

    oai_token-act-pair · gemini-2.0-flash

    San

    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
     pleaſure
    -0.66
     Monfieur
    -0.65
     quæ
    -0.65
     myſelf
    -0.63
     ſtate
    -0.60
     purpoſe
    -0.59
     sauvages
    -0.58
     barbati
    -0.58
     enfans
    -0.58
     avoient
    -0.58
    POSITIVE LOGITS
    <bos>
    0.57
     Cor
    0.54
     Fre
    0.51
     Dob
    0.51
     Tar
    0.50
     Cla
    0.50
     Ren
    0.50
     Gi
    0.49
     Av
    0.49
     Tur
    0.49
    Activations Density 2.715%

    No Known Activations