© 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. 11481
    Prev
    Next
    INDEX
    Explanations

    the tokens that immediately follow the 'dem' token within words

    oai_token-act-pair · gemini-2.0-flash

    dem/demo

    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
     demo
    -2.73
     demonstration
    -2.72
     Demonstr
    -2.58
     Demonstration
    -2.58
     Demo
    -2.58
     DEMON
    -2.53
    demon
    -2.53
    Demon
    -2.50
     demonstrations
    -2.48
     demos
    -2.47
    POSITIVE LOGITS
    AsUp
    0.56
     esternos
    0.55
    Skocz
    0.54
    bitkan
    0.54
    رشف
    0.51
    OrBuilder
    0.49
    RTDA
    0.49
     '\\;'
    0.48
    +:+
    0.48
    SPIRE
    0.47
    Activations Density 2.620%

    No Known Activations