© 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. 3267
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to government, medicine, and mechanical devices in some cases seeming to activate more for a combination of the topic areas.

    oai_token-act-pair · gemini-2.0-flash

    Technical contexts, "level"

    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
    Not in Any Lists

    No Comments

    Negative Logits
     a
    -0.66
     to
    -0.65
     is
    -0.64
     an
    -0.61
    e
    -0.60
    -
    -0.60
     it
    -0.59
     and
    -0.59
     the
    -0.58
    .
    -0.53
    POSITIVE LOGITS
     Roskov
    1.30
    StoryboardSegue
    1.16
    ValueStyle
    1.15
     AssemblyTitle
    1.05
    PreferredItem
    1.04
    CloseOperation
    1.04
     perpetuity
    1.04
     onOptions
    1.03
    FormTagHelper
    0.99
    AccessorTable
    0.98
    Activations Density 1.121%

    No Known Activations