© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11258
    Prev
    Next
    INDEX
    Explanations

    long runs of digits and nearby words about elections

    oai_token-act-pair · gemini-2.0-flash

    Multiples of 100

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    complexContent
    -0.86
     millions
    -0.68
    MigrationBuilder
    -0.66
    EndInit
    -0.64
    StreetMap
    -0.63
    NOPQRST
    -0.59
     Millions
    -0.59
    ImageContext
    -0.59
    fassung
    -0.58
    millions
    -0.58
    POSITIVE LOGITS
     hundred
    0.70
     hundreds
    0.57
     Hundred
    0.57
    hundred
    0.55
     Hundreds
    0.52
    fifty
    0.52
    Hundred
    0.52
     HUND
    0.51
     Seventy
    0.51
     Fifty
    0.51
    Activations Density 2.121%

    No Known Activations