© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8034
    Prev
    Next
    INDEX
    Explanations

    the word "pot" or "pots"

    oai_token-act-pair · gemini-2.0-flash

    pot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     ―――――
    -1.15
     Jefus
    -1.11
     ſeveral
    -1.09
     Monfieur
    -1.08
     Houſe
    -1.02
     itſelf
    -1.02
     ――――――――
    -1.00
     purpoſe
    -1.00
     pleaſure
    -1.00
     myſelf
    -0.98
    POSITIVE LOGITS
    <bos>
    0.72
    <>(
    0.65
    代
    0.62
     Text
    0.58
    QtWidgets
    0.57
    abes
    0.56
    حد
    0.55
     Ev
    0.55
     Ed
    0.55
     fin
    0.55
    Activations Density 2.035%

    No Known Activations