© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8342
    Prev
    Next
    INDEX
    Explanations

    words related to a sequence of actions to achieve something.

    oai_token-act-pair · gemini-2.0-flash

    process

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.74
     AssemblyProduct
    -0.56
    biet
    -0.56
     neutre
    -0.55
     unha
    -0.53
     gärna
    -0.53
     abstrait
    -0.53
     électronique
    -0.53
    apture
    -0.52
    addContainerGap
    -0.52
    POSITIVE LOGITS
    RenderAtEndOf
    0.82
    BagConstraints
    0.66
    ValueStyle
    0.62
    IsContent
    0.54
     OMIT
    0.52
     محفوظة
    0.52
    XmlAccessType
    0.51
    aarrggbb
    0.50
    ########.
    0.47
     gynhyrchwyd
    0.47
    Activations Density 0.920%

    No Known Activations