© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5822
    Prev
    Next
    INDEX
    Explanations

    words relating to growth or increasing

    oai_token-act-pair · gemini-2.0-flash

    grow

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    grow
    -0.86
     GROW
    -0.84
     дописавши
    -0.82
     grow
    -0.81
     growing
    -0.80
     Grow
    -0.79
    Grow
    -0.78
     Growing
    -0.75
    Growing
    -0.73
    GROW
    -0.73
    POSITIVE LOGITS
    WriteLiteral
    0.54
    快
    0.52
     into
    0.51
     toward
    0.50
     quicker
    0.50
     towards
    0.50
     faster
    0.49
     to
    0.48
    ChildScrollView
    0.47
     fast
    0.47
    Activations Density 3.707%

    No Known Activations