© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13602
    Prev
    Next
    INDEX
    Explanations

    sentences with "a" followed somewhat closely by a positive adjective or noun but also some other "positive" words nearby

    oai_token-act-pair · gemini-2.0-flash

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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>
    -0.95
     itſelf
    -0.84
     myſelf
    -0.83
     crdi
    -0.82
     ब्रेकडाउन
    -0.81
     Lordships
    -0.81
    ThroughAttribute
    -0.79
     Paglinawan
    -0.78
     doubtnut
    -0.77
    WithIOException
    -0.77
    POSITIVE LOGITS
     
    0.62
     value
    0.52
     $
    0.49
     thing
    0.49
     fly
    0.48
     ver
    0.48
    zusch
    0.48
    industan
    0.48
     &&
    0.48
    ід
    0.48
    Activations Density 4.742%

    No Known Activations