© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9258
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to achieving a goal, method, or technological process

    oai_token-act-pair · gemini-2.0-flash

    achieve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Achie
    -0.82
     achieves
    -0.76
    achieve
    -0.74
     gains
    -0.73
     achieve
    -0.71
    tvguidetime
    -0.71
    UnusedPrivate
    -0.69
     achieving
    -0.66
     Achieve
    -0.65
     Gains
    -0.65
    POSITIVE LOGITS
     referenties
    0.50
    apuram
    0.49
    undle
    0.49
     crested
    0.48
    lais
    0.48
    routeProvider
    0.47
    orija
    0.47
    endregion
    0.47
    mità
    0.47
    Rohy
    0.46
    Activations Density 25.253%

    No Known Activations