© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3024
    Prev
    Next
    INDEX
    Explanations

    the word "guy"

    oai_token-act-pair · gemini-2.0-flash

    guy

    np_max-act · gemini-2.0-flash

    guy

    np_max-act-logits · gpt-5-mini
    Triggered 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
    Negative Logits
     Theſe
    -2.06
     Monfieur
    -2.06
     Efq
    -1.93
     Anſ
    -1.89
     Houſe
    -1.84
     houſe
    -1.83
     myſelf
    -1.80
     pleaſure
    -1.79
     Jefus
    -1.71
     ſeveral
    -1.70
    POSITIVE LOGITS
     a
    1.05
    ,
    0.90
    </b>
    0.90
     the
    0.88
     (
    0.84
     sur
    0.82
     her
    0.81
     and
    0.81
     an
    0.79
     its
    0.78
    Activations Density 1.649%

    No Known Activations