© 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. 9885
    Prev
    Next
    INDEX
    Explanations

    the word "leave" and synonyms like depart

    oai_token-act-pair · gemini-2.0-flash

    leave

    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
     myſelf
    -1.32
    BeginContext
    -1.32
    EndContext
    -1.25
    +#+#
    -1.24
    ContentAsync
    -1.22
     Monfieur
    -1.20
    TagMode
    -1.20
    setVerticalGroup
    -1.18
     дописавши
    -1.18
     propOrder
    -1.15
    POSITIVE LOGITS
    ,
    0.89
    <bos>
    0.87
     the
    0.86
    ↵↵
    0.77
     a
    0.76
     and
    0.76
     
    0.73
     are
    0.72
     in
    0.71
    .
    0.70
    Activations Density 0.704%

    No Known Activations