© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12508
    Prev
    Next
    INDEX
    Explanations

    mentions of authority figures and dates within the same sentence

    oai_token-act-pair · gemini-2.0-flash

    succeed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     AssemblyProduct
    -0.90
     autorytatywna
    -0.77
    aarrggbb
    -0.74
    AddTagHelper
    -0.69
    setVerticalGroup
    -0.66
    MemoryWarning
    -0.66
     cherchés
    -0.65
    Viitteet
    -0.63
     getItemCount
    -0.62
    DebuggerNonUser
    -0.62
    POSITIVE LOGITS
     succeed
    2.58
     succeeds
    2.33
     succeeded
    2.33
     success
    2.13
     Success
    2.03
    Success
    1.97
    success
    1.84
     suc
    1.80
     Suc
    1.72
    succeeded
    1.70
    Activations Density 3.881%

    No Known Activations