© 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. 6141
    Prev
    Next
    INDEX
    Explanations

    mentions of clothing with emphasis on outer layers

    oai_token-act-pair · gemini-2.0-flash

    coat

    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
    ,
    -1.00
     “
    -0.95
    <strong>
    -0.93
    .
    -0.90
     
    -0.90
    ↵↵
    -0.87
     the
    -0.83
    “
    -0.82
     The
    -0.81
    The
    -0.81
    POSITIVE LOGITS
     myſelf
    1.28
     Theſe
    1.20
     Efq
    1.20
     himſelf
    1.17
     ―――――
    1.13
     iſt
    1.13
    !")
    1.13
     pleaſure
    1.11
     itſelf
    1.10
     Monfieur
    1.09
    Activations Density 5.834%

    No Known Activations