© 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. 8964
    Prev
    Next
    INDEX
    Explanations

    code-related words, specifically related to data storage and variables, and also seems to prefer the word "oneof".

    oai_token-act-pair · gemini-2.0-flash

    Code and numbers

    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
     Sion
    -0.94
     Sexton
    -0.91
     Pion
    -0.82
     Grafton
    -0.81
    CION
    -0.80
     Aragon
    -0.79
     Marlon
    -0.77
     Bison
    -0.77
     Lons
    -0.76
    ragon
    -0.74
    POSITIVE LOGITS
    ########.
    0.62
     Dunham
    0.60
     Lynne
    0.58
     Baile
    0.56
     Nomad
    0.54
     Pome
    0.53
                             
    0.51
     Reinh
    0.51
     linh
    0.51
     Cou
    0.51
    Activations Density 8.005%

    No Known Activations