© 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. 15296
    Prev
    Next
    INDEX
    Explanations

    text about formal ceremonies like graduation and sports broadcasting

    oai_token-act-pair · gemini-2.0-flash

    MC or Master

    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
    utschein
    -0.52
    thanes
    -0.48
     Borel
    -0.48
    DrawerToggle
    -0.47
    gazione
    -0.47
    corer
    -0.47
     Pollen
    -0.46
    MessageOf
    -0.45
    ajer
    -0.45
     kasarigan
    -0.44
    POSITIVE LOGITS
     em
    1.27
    Em
    1.04
     Em
    1.04
    em
    1.01
     MC
    0.98
     Master
    0.90
     master
    0.84
    master
    0.82
    Master
    0.81
     EM
    0.81
    Activations Density 4.682%

    No Known Activations