© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8164
    Prev
    Next
    INDEX
    Explanations

    words that are capitalized and/or related to legal agreements, studies, or military jargon

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    To
    -0.66
     To
    -0.66
    ToLeft
    -0.49
    abuhan
    -0.48
    akuan
    -0.45
     For
    -0.45
    %{
    -0.44
    pung
    -0.44
    IANT
    -0.43
    和我
    -0.43
    POSITIVE LOGITS
     The
    2.08
     THE
    2.00
    THE
    1.95
    The
    1.75
    the
    1.04
    sthe
    0.98
    enthe
    0.89
    Билгалдахарш
    0.88
     Thé
    0.83
    thew
    0.78
    Activations Density 8.215%

    No Known Activations