© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15388
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to biology and zoology.

    oai_token-act-pair · gemini-2.0-flash

    code-related keywords

    np_token-act-pair-logits · gpt-4o-mini

    insect metamorphosis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    MLLoader
    -0.76
     butterflies
    -0.63
     butterfly
    -0.61
     lizard
    -0.61
    usercontent
    -0.61
     nest
    -0.60
     hatch
    -0.59
     birds
    -0.59
     fish
    -0.58
     nests
    -0.58
    POSITIVE LOGITS
    cstdio
    0.52
    喱
    0.51
     članak
    0.49
    stdc
    0.48
     TextStyle
    0.47
    libft
    0.47
     Vero
    0.47
    AsUp
    0.47
    #+#
    0.47
    port
    0.45
    Activations Density 0.596%

    No Known Activations