© 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. 3041
    Prev
    Next
    INDEX
    Explanations

    when something is directed or related to power, gas, physical parts, or investigation

    oai_token-act-pair · gemini-2.0-flash

    directed

    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
    Negative Logits
     itſelf
    -1.99
     myſelf
    -1.95
     Efq
    -1.93
     ſind
    -1.73
    ſelf
    -1.71
    ^(@)
    -1.70
    ſelves
    -1.66
     ―――――
    -1.64
    BibitemShut
    -1.63
     iſt
    -1.61
    POSITIVE LOGITS
    ,
    1.12
    .
    0.94
    -
    0.92
    <eos>
    0.90
    1
    0.90
     
    0.88
     in
    0.88
    in
    0.87
    2
    0.85
     -
    0.85
    Activations Density 1.579%

    No Known Activations