© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12435
    Prev
    Next
    INDEX
    Explanations

    the word "oil" and words related to it

    oai_token-act-pair · gemini-2.0-flash

    oil

    np_max-act · gemini-2.0-flash

    oil

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     
    -1.61
    ,
    -1.50
      
    -1.41
    2
    -1.41
    1
    -1.38
    <eos>
    -1.38
    ↵↵
    -1.34
    '
    -1.32
     in
    -1.31
    3
    -1.31
    POSITIVE LOGITS
     Efq
    2.80
     Monfieur
    2.78
     myſelf
    2.70
     Jefus
    2.56
     Theſe
    2.53
     Majefty
    2.53
     pleaſure
    2.50
     ſeveral
    2.47
     purpoſe
    2.47
     houſe
    2.47
    Activations Density 4.724%

    No Known Activations