© 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. 12451
    Prev
    Next
    INDEX
    Explanations

    the words "hopes" and "generation," along with visual references "snow," and "just"

    oai_token-act-pair · gemini-2.0-flash

    desire, anticipation

    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
     متعلقه
    -1.14
    CodedInputStream
    -1.11
     idéia
    -0.90
     ویکی‌پدیا
    -0.89
    tagHelperRunner
    -0.88
    StoryboardSegue
    -0.86
    JspWriter
    -0.84
    TagMode
    -0.80
    BeginContext
    -0.79
     Administrativna
    -0.78
    POSITIVE LOGITS
    s
    0.62
     
    0.57
     
    0.54
     ‘
    0.52
     '
    0.52
     realisation
    0.51
    \#:
    0.50
    ↵
    0.49
     centre
    0.48
     total
    0.48
    Activations Density 0.820%

    No Known Activations