© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13916
    Prev
    Next
    INDEX
    Explanations

    words and terms about medicine and scientific research, including references.

    oai_token-act-pair · gemini-2.0-flash

    suffix fragments Method used: 3. Reason: top logits are token suffix fragments

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    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
    Negative Logits
    ting
    -1.42
    ly
    -1.24
    ness
    -1.21
    ity
    -1.19
    ling
    -1.14
    ing
    -1.02
    ding
    -0.98
    ally
    -0.98
    ation
    -0.98
    ned
    -0.96
    POSITIVE LOGITS
    solete
    0.82
    etCode
    0.80
    tvguidetime
    0.77
    rąg
    0.76
    FundMe
    0.73
     CURIAM
    0.70
    etcode
    0.69
    prnewswire
    0.69
    peech
    0.69
    vailability
    0.69
    Activations Density 24.149%

    No Known Activations