© 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. 15946
    Prev
    Next
    INDEX
    Explanations

    the word "have" and words close by

    oai_token-act-pair · gemini-2.0-flash

    have

    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
     have
    -2.02
     myſelf
    -1.53
     raiſ
    -1.29
     uſe
    -1.29
     Jefus
    -1.27
     ་་
    -1.27
    have
    -1.26
     itſelf
    -1.25
     uſed
    -1.24
     reaſon
    -1.20
    POSITIVE LOGITS
     Are
    0.82
    are
    0.75
    ARE
    0.75
     
    0.70
    Are
    0.70
    <eos>
    0.68
     a
    0.66
    aré
    0.63
     ARE
    0.61
    ↵
    0.61
    Activations Density 1.312%

    No Known Activations