© 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. 1535
    Prev
    Next
    INDEX
    Explanations

    author and editor initials

    oai_token-act-pair · gemini-2.0-flash

    uncommon or unique words

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

    Citations

    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
    Geografi
    -0.53
    setVerticalGroup
    -0.47
     propri
    -0.46
     Un
    -0.45
     den
    -0.43
    ]=-
    -0.43
    oth
    -0.42
     shop
    -0.42
     Ma
    -0.41
     un
    -0.40
    POSITIVE LOGITS
     AppColors
    0.83
     Normdatei
    0.83
     africains
    0.72
     pleaſure
    0.72
     ainfi
    0.72
     neceffary
    0.70
    KommentareTeilen
    0.70
     ſmall
    0.68
     ſeveral
    0.68
     raiſ
    0.67
    Activations Density 0.664%

    No Known Activations