© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5142
    Prev
    Next
    INDEX
    Explanations

    the word "contest"

    oai_token-act-pair · gemini-2.0-flash

    contest

    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
    <bos>
    -1.77
    ↵↵
    -1.76
     
    -1.63
    ↵
    -1.59
    <eos>
    -1.44
     the
    -1.30
      
    -1.27
    1
    -1.25
    2
    -1.23
     The
    -1.21
    POSITIVE LOGITS
     Efq
    2.23
     ―――――
    2.20
     Houſe
    2.14
     myſelf
    2.13
    ^(@)
    2.03
     doubtnut
    2.02
     $_"
    1.99
     Anſ
    1.98
     Majefty
    1.97
     Theſe
    1.96
    Activations Density 1.421%

    No Known Activations