© 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. 15750
    Prev
    Next
    INDEX
    Explanations

    the word "soon"

    oai_token-act-pair · gemini-2.0-flash

    soon

    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
    IntoConstraints
    -0.88
     myſelf
    -0.87
    TagMode
    -0.86
     ſeveral
    -0.85
    XmlAccessType
    -0.82
     itſelf
    -0.79
     Reſ
    -0.79
     Jefus
    -0.78
     Anſ
    -0.75
     himſelf
    -0.72
    POSITIVE LOGITS
     '
    0.65
     well
    0.61
     If
    0.57
     organised
    0.55
     ‘
    0.54
    ↵↵
    0.54
     programme
    0.52
     
    0.51
     colheres
    0.50
    setCancelable
    0.48
    Activations Density 0.383%

    No Known Activations