© 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. 11456
    Prev
    Next
    INDEX
    Explanations

    a variety of seemingly unrelated abbreviations, codes, and chemical terms

    oai_token-act-pair · gemini-2.0-flash

    sculpture and statues

    np_max-act-logits · 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
    ler
    -0.71
     le
    -0.69
    le
    -0.68
    ContentAsync
    -0.67
    LE
    -0.64
    les
    -0.59
    lé
    -0.58
    leos
    -0.58
    ling
    -0.57
    lers
    -0.57
    POSITIVE LOGITS
     sculpture
    1.35
     statue
    1.32
    Sculpture
    1.26
     Sculpture
    1.25
     statues
    1.25
     sculptures
    1.23
     monument
    1.18
    Scul
    1.16
    statue
    1.14
     Monument
    1.13
    Activations Density 0.727%

    No Known Activations